{
 "columns": [
  "session",
  "a",
  "b",
  "n",
  "brier_a",
  "brier_b",
  "diff",
  "diff_sum",
  "methodology_version",
  "event_ids",
  "kind"
 ],
 "kind": "council-pairs",
 "license": "CC BY 4.0",
 "metric": "brier_all_rows",
 "rows": [
  {
   "a": "chatgpt",
   "b": "claude",
   "brier_a": 0.2868,
   "brier_b": 0.2834,
   "diff": 0.0034,
   "diff_sum": 0.0375,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "chatgpt",
   "b": "deepseek",
   "brier_a": 0.2868,
   "brier_b": 0.2479,
   "diff": 0.0389,
   "diff_sum": 0.428,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "chatgpt",
   "b": "gemini",
   "brier_a": 0.2868,
   "brier_b": 0.283,
   "diff": 0.0038,
   "diff_sum": 0.0417,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "chatgpt",
   "b": "grok",
   "brier_a": 0.2868,
   "brier_b": 0.2636,
   "diff": 0.0232,
   "diff_sum": 0.2556,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "chatgpt",
   "b": "kimi",
   "brier_a": 0.2868,
   "brier_b": 0.2986,
   "diff": -0.0118,
   "diff_sum": -0.1296,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "chatgpt",
   "b": "mimo",
   "brier_a": 0.2852,
   "brier_b": 0.3463,
   "diff": -0.0611,
   "diff_sum": -0.6106,
   "event_ids": [
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 10,
   "session": "2026-10-19"
  },
  {
   "a": "claude",
   "b": "deepseek",
   "brier_a": 0.2834,
   "brier_b": 0.2479,
   "diff": 0.0355,
   "diff_sum": 0.3905,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "claude",
   "b": "gemini",
   "brier_a": 0.2834,
   "brier_b": 0.283,
   "diff": 0.0004,
   "diff_sum": 0.0042,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2834,
   "brier_b": 0.2636,
   "diff": 0.0198,
   "diff_sum": 0.2181,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "claude",
   "b": "kimi",
   "brier_a": 0.2834,
   "brier_b": 0.2986,
   "diff": -0.0152,
   "diff_sum": -0.1671,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2836,
   "brier_b": 0.3463,
   "diff": -0.0626,
   "diff_sum": -0.6265,
   "event_ids": [
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 10,
   "session": "2026-10-19"
  },
  {
   "a": "deepseek",
   "b": "gemini",
   "brier_a": 0.2479,
   "brier_b": 0.283,
   "diff": -0.0351,
   "diff_sum": -0.3863,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "deepseek",
   "b": "grok",
   "brier_a": 0.2479,
   "brier_b": 0.2636,
   "diff": -0.0157,
   "diff_sum": -0.1724,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "deepseek",
   "b": "kimi",
   "brier_a": 0.2479,
   "brier_b": 0.2986,
   "diff": -0.0507,
   "diff_sum": -0.5576,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "deepseek",
   "b": "mimo",
   "brier_a": 0.2524,
   "brier_b": 0.3463,
   "diff": -0.0939,
   "diff_sum": -0.9386,
   "event_ids": [
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 10,
   "session": "2026-10-19"
  },
  {
   "a": "gemini",
   "b": "grok",
   "brier_a": 0.283,
   "brier_b": 0.2636,
   "diff": 0.0194,
   "diff_sum": 0.2139,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "gemini",
   "b": "kimi",
   "brier_a": 0.283,
   "brier_b": 0.2986,
   "diff": -0.0156,
   "diff_sum": -0.1713,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "gemini",
   "b": "mimo",
   "brier_a": 0.2911,
   "brier_b": 0.3463,
   "diff": -0.0552,
   "diff_sum": -0.5523,
   "event_ids": [
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 10,
   "session": "2026-10-19"
  },
  {
   "a": "grok",
   "b": "kimi",
   "brier_a": 0.2636,
   "brier_b": 0.2986,
   "diff": -0.035,
   "diff_sum": -0.3852,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.2669,
   "brier_b": 0.3463,
   "diff": -0.0794,
   "diff_sum": -0.7941,
   "event_ids": [
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 10,
   "session": "2026-10-19"
  },
  {
   "a": "kimi",
   "b": "mimo",
   "brier_a": 0.29,
   "brier_b": 0.3463,
   "diff": -0.0563,
   "diff_sum": -0.5629,
   "event_ids": [
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "model_pair",
   "methodology_version": "m1",
   "n": 10,
   "session": "2026-10-19"
  },
  {
   "a": "chatgpt",
   "b": "claude",
   "brier_a": 0.2737,
   "brier_b": 0.2601,
   "diff": 0.0136,
   "diff_sum": 0.1493,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "deepseek",
   "brier_a": 0.2729,
   "brier_b": 0.2918,
   "diff": -0.0188,
   "diff_sum": -0.1883,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "gemini",
   "brier_a": 0.2725,
   "brier_b": 0.2865,
   "diff": -0.0139,
   "diff_sum": -0.167,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 12,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "grok",
   "brier_a": 0.2789,
   "brier_b": 0.2814,
   "diff": -0.0025,
   "diff_sum": -0.0222,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "meta",
   "brier_a": 0.2783,
   "brier_b": 0.2383,
   "diff": 0.0399,
   "diff_sum": 0.3195,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-b7f50239bd3df4b8",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 8,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "mimo",
   "brier_a": 0.2737,
   "brier_b": 0.2913,
   "diff": -0.0177,
   "diff_sum": -0.1943,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "stepfun",
   "brier_a": 0.2755,
   "brier_b": 0.2845,
   "diff": -0.0091,
   "diff_sum": -0.0996,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "wenxin",
   "brier_a": 0.2755,
   "brier_b": 0.3267,
   "diff": -0.0512,
   "diff_sum": -0.5629,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "deepseek",
   "brier_a": 0.258,
   "brier_b": 0.2918,
   "diff": -0.0338,
   "diff_sum": -0.3376,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "gemini",
   "brier_a": 0.2601,
   "brier_b": 0.2957,
   "diff": -0.0356,
   "diff_sum": -0.3915,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2656,
   "brier_b": 0.2814,
   "diff": -0.0158,
   "diff_sum": -0.1418,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "meta",
   "brier_a": 0.26,
   "brier_b": 0.2352,
   "diff": 0.0248,
   "diff_sum": 0.1734,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 7,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2601,
   "brier_b": 0.2913,
   "diff": -0.0312,
   "diff_sum": -0.3436,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "stepfun",
   "brier_a": 0.2621,
   "brier_b": 0.286,
   "diff": -0.0239,
   "diff_sum": -0.2386,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "claude",
   "b": "wenxin",
   "brier_a": 0.2621,
   "brier_b": 0.3353,
   "diff": -0.0732,
   "diff_sum": -0.7322,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "deepseek",
   "b": "gemini",
   "brier_a": 0.2918,
   "brier_b": 0.305,
   "diff": -0.0132,
   "diff_sum": -0.1323,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "deepseek",
   "b": "grok",
   "brier_a": 0.3009,
   "brier_b": 0.2814,
   "diff": 0.0195,
   "diff_sum": 0.1558,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 8,
   "session": "2026-10-20"
  },
  {
   "a": "deepseek",
   "b": "meta",
   "brier_a": 0.3004,
   "brier_b": 0.236,
   "diff": 0.0643,
   "diff_sum": 0.386,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 6,
   "session": "2026-10-20"
  },
  {
   "a": "deepseek",
   "b": "mimo",
   "brier_a": 0.2918,
   "brier_b": 0.2913,
   "diff": 0.0005,
   "diff_sum": 0.0047,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "deepseek",
   "b": "stepfun",
   "brier_a": 0.2975,
   "brier_b": 0.2829,
   "diff": 0.0146,
   "diff_sum": 0.1317,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "deepseek",
   "b": "wenxin",
   "brier_a": 0.2975,
   "brier_b": 0.3425,
   "diff": -0.045,
   "diff_sum": -0.4051,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "gemini",
   "b": "grok",
   "brier_a": 0.304,
   "brier_b": 0.2814,
   "diff": 0.0227,
   "diff_sum": 0.2041,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "gemini",
   "b": "meta",
   "brier_a": 0.2914,
   "brier_b": 0.2383,
   "diff": 0.0531,
   "diff_sum": 0.4248,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-b7f50239bd3df4b8",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 8,
   "session": "2026-10-20"
  },
  {
   "a": "gemini",
   "b": "mimo",
   "brier_a": 0.2957,
   "brier_b": 0.2913,
   "diff": 0.0044,
   "diff_sum": 0.0479,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "gemini",
   "b": "stepfun",
   "brier_a": 0.2941,
   "brier_b": 0.2845,
   "diff": 0.0095,
   "diff_sum": 0.105,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "gemini",
   "b": "wenxin",
   "brier_a": 0.2941,
   "brier_b": 0.3267,
   "diff": -0.0326,
   "diff_sum": -0.3583,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "grok",
   "b": "meta",
   "brier_a": 0.2816,
   "brier_b": 0.2294,
   "diff": 0.0522,
   "diff_sum": 0.3132,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 6,
   "session": "2026-10-20"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.2814,
   "brier_b": 0.2993,
   "diff": -0.018,
   "diff_sum": -0.1618,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "grok",
   "b": "stepfun",
   "brier_a": 0.2814,
   "brier_b": 0.2877,
   "diff": -0.0063,
   "diff_sum": -0.0568,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "grok",
   "b": "wenxin",
   "brier_a": 0.2814,
   "brier_b": 0.3425,
   "diff": -0.0612,
   "diff_sum": -0.5504,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 9,
   "session": "2026-10-20"
  },
  {
   "a": "meta",
   "b": "mimo",
   "brier_a": 0.2352,
   "brier_b": 0.2923,
   "diff": -0.057,
   "diff_sum": -0.3993,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 7,
   "session": "2026-10-20"
  },
  {
   "a": "meta",
   "b": "stepfun",
   "brier_a": 0.2383,
   "brier_b": 0.2819,
   "diff": -0.0435,
   "diff_sum": -0.3482,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-b7f50239bd3df4b8",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 8,
   "session": "2026-10-20"
  },
  {
   "a": "meta",
   "b": "wenxin",
   "brier_a": 0.2383,
   "brier_b": 0.3282,
   "diff": -0.0899,
   "diff_sum": -0.7191,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-b7f50239bd3df4b8",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 8,
   "session": "2026-10-20"
  },
  {
   "a": "mimo",
   "b": "stepfun",
   "brier_a": 0.2964,
   "brier_b": 0.286,
   "diff": 0.0105,
   "diff_sum": 0.105,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "mimo",
   "b": "wenxin",
   "brier_a": 0.2964,
   "brier_b": 0.3353,
   "diff": -0.0389,
   "diff_sum": -0.3886,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 10,
   "session": "2026-10-20"
  },
  {
   "a": "stepfun",
   "b": "wenxin",
   "brier_a": 0.2845,
   "brier_b": 0.3267,
   "diff": -0.0421,
   "diff_sum": -0.4633,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "model_pair",
   "methodology_version": "m2",
   "n": 11,
   "session": "2026-10-20"
  },
  {
   "a": "chatgpt",
   "b": "claude",
   "brier_a": 0.2425,
   "brier_b": 0.2448,
   "diff": -0.0023,
   "diff_sum": -0.0271,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "deepseek",
   "brier_a": 0.2425,
   "brier_b": 0.2188,
   "diff": 0.0238,
   "diff_sum": 0.285,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "gemini",
   "brier_a": 0.2425,
   "brier_b": 0.236,
   "diff": 0.0066,
   "diff_sum": 0.0788,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "grok",
   "brier_a": 0.2425,
   "brier_b": 0.2027,
   "diff": 0.0399,
   "diff_sum": 0.4783,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "meta",
   "brier_a": 0.2462,
   "brier_b": 0.2007,
   "diff": 0.0454,
   "diff_sum": 0.4999,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "mimo",
   "brier_a": 0.2425,
   "brier_b": 0.2391,
   "diff": 0.0034,
   "diff_sum": 0.041,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "stepfun",
   "brier_a": 0.2425,
   "brier_b": 0.2315,
   "diff": 0.011,
   "diff_sum": 0.1318,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "zai",
   "brier_a": 0.2425,
   "brier_b": 0.2335,
   "diff": 0.009,
   "diff_sum": 0.1077,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "deepseek",
   "brier_a": 0.2448,
   "brier_b": 0.2188,
   "diff": 0.026,
   "diff_sum": 0.3121,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "gemini",
   "brier_a": 0.2448,
   "brier_b": 0.236,
   "diff": 0.0088,
   "diff_sum": 0.1059,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2448,
   "brier_b": 0.2027,
   "diff": 0.0421,
   "diff_sum": 0.5054,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "meta",
   "brier_a": 0.2443,
   "brier_b": 0.2007,
   "diff": 0.0436,
   "diff_sum": 0.4795,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2448,
   "brier_b": 0.2391,
   "diff": 0.0057,
   "diff_sum": 0.0681,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "stepfun",
   "brier_a": 0.2448,
   "brier_b": 0.2315,
   "diff": 0.0132,
   "diff_sum": 0.1589,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "claude",
   "b": "zai",
   "brier_a": 0.2448,
   "brier_b": 0.2335,
   "diff": 0.0112,
   "diff_sum": 0.1348,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "deepseek",
   "b": "gemini",
   "brier_a": 0.2188,
   "brier_b": 0.236,
   "diff": -0.0172,
   "diff_sum": -0.2062,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "deepseek",
   "b": "grok",
   "brier_a": 0.2188,
   "brier_b": 0.2027,
   "diff": 0.0161,
   "diff_sum": 0.1933,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "deepseek",
   "b": "meta",
   "brier_a": 0.2241,
   "brier_b": 0.2007,
   "diff": 0.0234,
   "diff_sum": 0.2574,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "deepseek",
   "b": "mimo",
   "brier_a": 0.2188,
   "brier_b": 0.2391,
   "diff": -0.0203,
   "diff_sum": -0.244,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "deepseek",
   "b": "stepfun",
   "brier_a": 0.2188,
   "brier_b": 0.2315,
   "diff": -0.0128,
   "diff_sum": -0.1532,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "deepseek",
   "b": "zai",
   "brier_a": 0.2188,
   "brier_b": 0.2335,
   "diff": -0.0148,
   "diff_sum": -0.1773,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "gemini",
   "b": "grok",
   "brier_a": 0.236,
   "brier_b": 0.2027,
   "diff": 0.0333,
   "diff_sum": 0.3995,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "gemini",
   "b": "meta",
   "brier_a": 0.2299,
   "brier_b": 0.2007,
   "diff": 0.0292,
   "diff_sum": 0.3211,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "gemini",
   "b": "mimo",
   "brier_a": 0.236,
   "brier_b": 0.2391,
   "diff": -0.0031,
   "diff_sum": -0.0378,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "gemini",
   "b": "stepfun",
   "brier_a": 0.236,
   "brier_b": 0.2315,
   "diff": 0.0044,
   "diff_sum": 0.053,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "gemini",
   "b": "zai",
   "brier_a": 0.236,
   "brier_b": 0.2335,
   "diff": 0.0024,
   "diff_sum": 0.0289,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "grok",
   "b": "meta",
   "brier_a": 0.2001,
   "brier_b": 0.2007,
   "diff": -0.0006,
   "diff_sum": -0.0063,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.2027,
   "brier_b": 0.2391,
   "diff": -0.0364,
   "diff_sum": -0.4373,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "grok",
   "b": "stepfun",
   "brier_a": 0.2027,
   "brier_b": 0.2315,
   "diff": -0.0289,
   "diff_sum": -0.3465,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "grok",
   "b": "zai",
   "brier_a": 0.2027,
   "brier_b": 0.2335,
   "diff": -0.0309,
   "diff_sum": -0.3706,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "meta",
   "b": "mimo",
   "brier_a": 0.2007,
   "brier_b": 0.2432,
   "diff": -0.0425,
   "diff_sum": -0.4678,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "meta",
   "b": "stepfun",
   "brier_a": 0.2007,
   "brier_b": 0.2316,
   "diff": -0.0309,
   "diff_sum": -0.3402,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "meta",
   "b": "zai",
   "brier_a": 0.2007,
   "brier_b": 0.2364,
   "diff": -0.0357,
   "diff_sum": -0.3922,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "mimo",
   "b": "stepfun",
   "brier_a": 0.2391,
   "brier_b": 0.2315,
   "diff": 0.0076,
   "diff_sum": 0.0908,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "mimo",
   "b": "zai",
   "brier_a": 0.2391,
   "brier_b": 0.2335,
   "diff": 0.0056,
   "diff_sum": 0.0667,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "stepfun",
   "b": "zai",
   "brier_a": 0.2315,
   "brier_b": 0.2335,
   "diff": -0.002,
   "diff_sum": -0.0241,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "model_pair",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "chatgpt",
   "b": "claude",
   "brier_a": 0.1959,
   "brier_b": 0.2523,
   "diff": -0.0564,
   "diff_sum": -0.6764,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "deepseek",
   "brier_a": 0.1959,
   "brier_b": 0.2188,
   "diff": -0.0229,
   "diff_sum": -0.2747,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "gemini",
   "brier_a": 0.1999,
   "brier_b": 0.233,
   "diff": -0.0332,
   "diff_sum": -0.3649,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "grok",
   "brier_a": 0.1959,
   "brier_b": 0.1862,
   "diff": 0.0097,
   "diff_sum": 0.1158,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "meta",
   "brier_a": 0.1999,
   "brier_b": 0.2102,
   "diff": -0.0104,
   "diff_sum": -0.114,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "mimo",
   "brier_a": 0.1959,
   "brier_b": 0.2135,
   "diff": -0.0176,
   "diff_sum": -0.2115,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "stepfun",
   "brier_a": 0.1959,
   "brier_b": 0.2217,
   "diff": -0.0258,
   "diff_sum": -0.3095,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "chatgpt",
   "b": "zai",
   "brier_a": 0.1959,
   "brier_b": 0.2542,
   "diff": -0.0583,
   "diff_sum": -0.6994,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "deepseek",
   "brier_a": 0.2523,
   "brier_b": 0.2188,
   "diff": 0.0335,
   "diff_sum": 0.4017,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "gemini",
   "brier_a": 0.2542,
   "brier_b": 0.233,
   "diff": 0.0212,
   "diff_sum": 0.2332,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2523,
   "brier_b": 0.1862,
   "diff": 0.066,
   "diff_sum": 0.7922,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "meta",
   "brier_a": 0.2542,
   "brier_b": 0.2102,
   "diff": 0.044,
   "diff_sum": 0.4841,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2523,
   "brier_b": 0.2135,
   "diff": 0.0387,
   "diff_sum": 0.4649,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "stepfun",
   "brier_a": 0.2523,
   "brier_b": 0.2217,
   "diff": 0.0306,
   "diff_sum": 0.3669,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "zai",
   "brier_a": 0.2523,
   "brier_b": 0.2542,
   "diff": -0.0019,
   "diff_sum": -0.023,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "deepseek",
   "b": "gemini",
   "brier_a": 0.2211,
   "brier_b": 0.233,
   "diff": -0.012,
   "diff_sum": -0.1317,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "deepseek",
   "b": "grok",
   "brier_a": 0.2188,
   "brier_b": 0.1862,
   "diff": 0.0325,
   "diff_sum": 0.3905,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "deepseek",
   "b": "meta",
   "brier_a": 0.2211,
   "brier_b": 0.2102,
   "diff": 0.0108,
   "diff_sum": 0.1192,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "deepseek",
   "b": "mimo",
   "brier_a": 0.2188,
   "brier_b": 0.2135,
   "diff": 0.0053,
   "diff_sum": 0.0632,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "deepseek",
   "b": "stepfun",
   "brier_a": 0.2188,
   "brier_b": 0.2217,
   "diff": -0.0029,
   "diff_sum": -0.0348,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "deepseek",
   "b": "zai",
   "brier_a": 0.2188,
   "brier_b": 0.2542,
   "diff": -0.0354,
   "diff_sum": -0.4247,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "gemini",
   "b": "grok",
   "brier_a": 0.233,
   "brier_b": 0.192,
   "diff": 0.041,
   "diff_sum": 0.4511,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "gemini",
   "b": "meta",
   "brier_a": 0.233,
   "brier_b": 0.2102,
   "diff": 0.0228,
   "diff_sum": 0.2509,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "gemini",
   "b": "mimo",
   "brier_a": 0.233,
   "brier_b": 0.2161,
   "diff": 0.0169,
   "diff_sum": 0.1862,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "gemini",
   "b": "stepfun",
   "brier_a": 0.233,
   "brier_b": 0.2242,
   "diff": 0.0088,
   "diff_sum": 0.0969,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "gemini",
   "b": "zai",
   "brier_a": 0.233,
   "brier_b": 0.2589,
   "diff": -0.0258,
   "diff_sum": -0.2841,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "grok",
   "b": "meta",
   "brier_a": 0.192,
   "brier_b": 0.2102,
   "diff": -0.0182,
   "diff_sum": -0.2002,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.1862,
   "brier_b": 0.2135,
   "diff": -0.0273,
   "diff_sum": -0.3273,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "grok",
   "b": "stepfun",
   "brier_a": 0.1862,
   "brier_b": 0.2217,
   "diff": -0.0354,
   "diff_sum": -0.4253,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "grok",
   "b": "zai",
   "brier_a": 0.1862,
   "brier_b": 0.2542,
   "diff": -0.0679,
   "diff_sum": -0.8152,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "meta",
   "b": "mimo",
   "brier_a": 0.2102,
   "brier_b": 0.2161,
   "diff": -0.0059,
   "diff_sum": -0.0647,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "meta",
   "b": "stepfun",
   "brier_a": 0.2102,
   "brier_b": 0.2242,
   "diff": -0.014,
   "diff_sum": -0.154,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "meta",
   "b": "zai",
   "brier_a": 0.2102,
   "brier_b": 0.2589,
   "diff": -0.0486,
   "diff_sum": -0.535,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-22"
  },
  {
   "a": "mimo",
   "b": "stepfun",
   "brier_a": 0.2135,
   "brier_b": 0.2217,
   "diff": -0.0082,
   "diff_sum": -0.098,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "mimo",
   "b": "zai",
   "brier_a": 0.2135,
   "brier_b": 0.2542,
   "diff": -0.0407,
   "diff_sum": -0.4879,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "stepfun",
   "b": "zai",
   "brier_a": 0.2217,
   "brier_b": 0.2542,
   "diff": -0.0325,
   "diff_sum": -0.3899,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "claude",
   "b": "deepseek",
   "brier_a": 0.2296,
   "brier_b": 0.2306,
   "diff": -0.001,
   "diff_sum": -0.0121,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2296,
   "brier_b": 0.2764,
   "diff": -0.0468,
   "diff_sum": -0.5613,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "claude",
   "b": "kimi",
   "brier_a": 0.2304,
   "brier_b": 0.2546,
   "diff": -0.0242,
   "diff_sum": -0.2663,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "claude",
   "b": "meta",
   "brier_a": 0.2304,
   "brier_b": 0.2221,
   "diff": 0.0083,
   "diff_sum": 0.0913,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2296,
   "brier_b": 0.2035,
   "diff": 0.0261,
   "diff_sum": 0.3137,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "claude",
   "b": "nemotron",
   "brier_a": 0.2304,
   "brier_b": 0.328,
   "diff": -0.0976,
   "diff_sum": -1.0738,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "claude",
   "b": "zai",
   "brier_a": 0.2296,
   "brier_b": 0.2176,
   "diff": 0.0121,
   "diff_sum": 0.1449,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "deepseek",
   "b": "grok",
   "brier_a": 0.2306,
   "brier_b": 0.2764,
   "diff": -0.0458,
   "diff_sum": -0.5492,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "deepseek",
   "b": "kimi",
   "brier_a": 0.2332,
   "brier_b": 0.2546,
   "diff": -0.0214,
   "diff_sum": -0.2358,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "deepseek",
   "b": "meta",
   "brier_a": 0.2332,
   "brier_b": 0.2221,
   "diff": 0.0111,
   "diff_sum": 0.1218,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "deepseek",
   "b": "mimo",
   "brier_a": 0.2306,
   "brier_b": 0.2035,
   "diff": 0.0272,
   "diff_sum": 0.3258,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "deepseek",
   "b": "nemotron",
   "brier_a": 0.2332,
   "brier_b": 0.328,
   "diff": -0.0948,
   "diff_sum": -1.0433,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "deepseek",
   "b": "zai",
   "brier_a": 0.2306,
   "brier_b": 0.2176,
   "diff": 0.0131,
   "diff_sum": 0.157,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "grok",
   "b": "kimi",
   "brier_a": 0.2806,
   "brier_b": 0.2546,
   "diff": 0.026,
   "diff_sum": 0.2855,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "grok",
   "b": "meta",
   "brier_a": 0.2806,
   "brier_b": 0.2221,
   "diff": 0.0585,
   "diff_sum": 0.6431,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.2764,
   "brier_b": 0.2035,
   "diff": 0.0729,
   "diff_sum": 0.875,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "grok",
   "b": "nemotron",
   "brier_a": 0.2806,
   "brier_b": 0.328,
   "diff": -0.0475,
   "diff_sum": -0.522,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "grok",
   "b": "zai",
   "brier_a": 0.2764,
   "brier_b": 0.2176,
   "diff": 0.0589,
   "diff_sum": 0.7062,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "kimi",
   "b": "meta",
   "brier_a": 0.2546,
   "brier_b": 0.2221,
   "diff": 0.0325,
   "diff_sum": 0.3576,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "kimi",
   "b": "mimo",
   "brier_a": 0.2546,
   "brier_b": 0.1993,
   "diff": 0.0554,
   "diff_sum": 0.6091,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "kimi",
   "b": "nemotron",
   "brier_a": 0.2546,
   "brier_b": 0.328,
   "diff": -0.0734,
   "diff_sum": -0.8075,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "kimi",
   "b": "zai",
   "brier_a": 0.2546,
   "brier_b": 0.2173,
   "diff": 0.0374,
   "diff_sum": 0.4112,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "meta",
   "b": "mimo",
   "brier_a": 0.2221,
   "brier_b": 0.1993,
   "diff": 0.0229,
   "diff_sum": 0.2515,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "meta",
   "b": "nemotron",
   "brier_a": 0.2221,
   "brier_b": 0.328,
   "diff": -0.1059,
   "diff_sum": -1.1651,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "meta",
   "b": "zai",
   "brier_a": 0.2221,
   "brier_b": 0.2173,
   "diff": 0.0049,
   "diff_sum": 0.0536,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "mimo",
   "b": "nemotron",
   "brier_a": 0.1993,
   "brier_b": 0.328,
   "diff": -0.1288,
   "diff_sum": -1.4166,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "mimo",
   "b": "zai",
   "brier_a": 0.2035,
   "brier_b": 0.2176,
   "diff": -0.0141,
   "diff_sum": -0.1688,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "nemotron",
   "b": "zai",
   "brier_a": 0.328,
   "brier_b": 0.2173,
   "diff": 0.1108,
   "diff_sum": 1.2187,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-23"
  },
  {
   "a": "chatgpt",
   "b": "claude",
   "brier_a": 0.247,
   "brier_b": 0.2435,
   "diff": 0.0035,
   "diff_sum": 0.042,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "gemini",
   "brier_a": 0.247,
   "brier_b": 0.2444,
   "diff": 0.0026,
   "diff_sum": 0.0315,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "grok",
   "brier_a": 0.247,
   "brier_b": 0.2418,
   "diff": 0.0052,
   "diff_sum": 0.0623,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "kimi",
   "brier_a": 0.247,
   "brier_b": 0.2437,
   "diff": 0.0033,
   "diff_sum": 0.0394,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "meta",
   "brier_a": 0.247,
   "brier_b": 0.237,
   "diff": 0.01,
   "diff_sum": 0.12,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "mimo",
   "brier_a": 0.247,
   "brier_b": 0.2427,
   "diff": 0.0043,
   "diff_sum": 0.0513,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "qwen",
   "brier_a": 0.247,
   "brier_b": 0.2471,
   "diff": -0.0001,
   "diff_sum": -0.0007,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "stepfun",
   "brier_a": 0.2494,
   "brier_b": 0.2434,
   "diff": 0.006,
   "diff_sum": 0.0655,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "chatgpt",
   "b": "zai",
   "brier_a": 0.247,
   "brier_b": 0.2342,
   "diff": 0.0128,
   "diff_sum": 0.1533,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "gemini",
   "brier_a": 0.2435,
   "brier_b": 0.2444,
   "diff": -0.0009,
   "diff_sum": -0.0105,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2435,
   "brier_b": 0.2418,
   "diff": 0.0017,
   "diff_sum": 0.0203,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "kimi",
   "brier_a": 0.2435,
   "brier_b": 0.2437,
   "diff": -0.0002,
   "diff_sum": -0.0026,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "meta",
   "brier_a": 0.2435,
   "brier_b": 0.237,
   "diff": 0.0065,
   "diff_sum": 0.078,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2435,
   "brier_b": 0.2427,
   "diff": 0.0008,
   "diff_sum": 0.0093,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "qwen",
   "brier_a": 0.2435,
   "brier_b": 0.2471,
   "diff": -0.0036,
   "diff_sum": -0.0427,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "stepfun",
   "brier_a": 0.2447,
   "brier_b": 0.2434,
   "diff": 0.0013,
   "diff_sum": 0.014,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "zai",
   "brier_a": 0.2435,
   "brier_b": 0.2342,
   "diff": 0.0093,
   "diff_sum": 0.1113,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "grok",
   "brier_a": 0.2444,
   "brier_b": 0.2418,
   "diff": 0.0026,
   "diff_sum": 0.0308,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "kimi",
   "brier_a": 0.2444,
   "brier_b": 0.2437,
   "diff": 0.0007,
   "diff_sum": 0.0079,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "meta",
   "brier_a": 0.2444,
   "brier_b": 0.237,
   "diff": 0.0074,
   "diff_sum": 0.0885,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "mimo",
   "brier_a": 0.2444,
   "brier_b": 0.2427,
   "diff": 0.0017,
   "diff_sum": 0.0198,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "qwen",
   "brier_a": 0.2444,
   "brier_b": 0.2471,
   "diff": -0.0027,
   "diff_sum": -0.0322,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "stepfun",
   "brier_a": 0.249,
   "brier_b": 0.2434,
   "diff": 0.0056,
   "diff_sum": 0.0613,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "gemini",
   "b": "zai",
   "brier_a": 0.2444,
   "brier_b": 0.2342,
   "diff": 0.0102,
   "diff_sum": 0.1218,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "grok",
   "b": "kimi",
   "brier_a": 0.2418,
   "brier_b": 0.2437,
   "diff": -0.0019,
   "diff_sum": -0.0229,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "grok",
   "b": "meta",
   "brier_a": 0.2418,
   "brier_b": 0.237,
   "diff": 0.0048,
   "diff_sum": 0.0577,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.2418,
   "brier_b": 0.2427,
   "diff": -0.0009,
   "diff_sum": -0.011,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "grok",
   "b": "qwen",
   "brier_a": 0.2418,
   "brier_b": 0.2471,
   "diff": -0.0053,
   "diff_sum": -0.063,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "grok",
   "b": "stepfun",
   "brier_a": 0.2392,
   "brier_b": 0.2434,
   "diff": -0.0042,
   "diff_sum": -0.0463,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "grok",
   "b": "zai",
   "brier_a": 0.2418,
   "brier_b": 0.2342,
   "diff": 0.0076,
   "diff_sum": 0.091,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "kimi",
   "b": "meta",
   "brier_a": 0.2437,
   "brier_b": 0.237,
   "diff": 0.0067,
   "diff_sum": 0.0806,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "kimi",
   "b": "mimo",
   "brier_a": 0.2437,
   "brier_b": 0.2427,
   "diff": 0.001,
   "diff_sum": 0.0119,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "kimi",
   "b": "qwen",
   "brier_a": 0.2437,
   "brier_b": 0.2471,
   "diff": -0.0033,
   "diff_sum": -0.0401,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "kimi",
   "b": "stepfun",
   "brier_a": 0.2413,
   "brier_b": 0.2434,
   "diff": -0.0021,
   "diff_sum": -0.0234,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "kimi",
   "b": "zai",
   "brier_a": 0.2437,
   "brier_b": 0.2342,
   "diff": 0.0095,
   "diff_sum": 0.1139,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "meta",
   "b": "mimo",
   "brier_a": 0.237,
   "brier_b": 0.2427,
   "diff": -0.0057,
   "diff_sum": -0.0687,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "meta",
   "b": "qwen",
   "brier_a": 0.237,
   "brier_b": 0.2471,
   "diff": -0.0101,
   "diff_sum": -0.1207,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "meta",
   "b": "stepfun",
   "brier_a": 0.234,
   "brier_b": 0.2434,
   "diff": -0.0095,
   "diff_sum": -0.104,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "meta",
   "b": "zai",
   "brier_a": 0.237,
   "brier_b": 0.2342,
   "diff": 0.0028,
   "diff_sum": 0.0333,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "mimo",
   "b": "qwen",
   "brier_a": 0.2427,
   "brier_b": 0.2471,
   "diff": -0.0043,
   "diff_sum": -0.052,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "mimo",
   "b": "stepfun",
   "brier_a": 0.2393,
   "brier_b": 0.2434,
   "diff": -0.0042,
   "diff_sum": -0.0458,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "mimo",
   "b": "zai",
   "brier_a": 0.2427,
   "brier_b": 0.2342,
   "diff": 0.0085,
   "diff_sum": 0.102,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "qwen",
   "b": "stepfun",
   "brier_a": 0.242,
   "brier_b": 0.2434,
   "diff": -0.0014,
   "diff_sum": -0.0154,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "qwen",
   "b": "zai",
   "brier_a": 0.2471,
   "brier_b": 0.2342,
   "diff": 0.0128,
   "diff_sum": 0.154,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "stepfun",
   "b": "zai",
   "brier_a": 0.2434,
   "brier_b": 0.2309,
   "diff": 0.0125,
   "diff_sum": 0.1373,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "claude",
   "b": "gemini",
   "brier_a": 0.2467,
   "brier_b": 0.2725,
   "diff": -0.0257,
   "diff_sum": -0.3086,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "claude",
   "b": "grok",
   "brier_a": 0.2467,
   "brier_b": 0.2639,
   "diff": -0.0172,
   "diff_sum": -0.2061,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "claude",
   "b": "kimi",
   "brier_a": 0.2467,
   "brier_b": 0.2824,
   "diff": -0.0356,
   "diff_sum": -0.4275,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "claude",
   "b": "meta",
   "brier_a": 0.2467,
   "brier_b": 0.2636,
   "diff": -0.0168,
   "diff_sum": -0.2021,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "claude",
   "b": "mimo",
   "brier_a": 0.2467,
   "brier_b": 0.2601,
   "diff": -0.0134,
   "diff_sum": -0.1604,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "claude",
   "b": "qwen",
   "brier_a": 0.2467,
   "brier_b": 0.1993,
   "diff": 0.0475,
   "diff_sum": 0.5695,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "claude",
   "b": "zai",
   "brier_a": 0.2467,
   "brier_b": 0.2543,
   "diff": -0.0076,
   "diff_sum": -0.0911,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "gemini",
   "b": "grok",
   "brier_a": 0.2725,
   "brier_b": 0.2639,
   "diff": 0.0085,
   "diff_sum": 0.1025,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "gemini",
   "b": "kimi",
   "brier_a": 0.2725,
   "brier_b": 0.2824,
   "diff": -0.0099,
   "diff_sum": -0.1189,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "gemini",
   "b": "meta",
   "brier_a": 0.2725,
   "brier_b": 0.2636,
   "diff": 0.0089,
   "diff_sum": 0.1065,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "gemini",
   "b": "mimo",
   "brier_a": 0.2725,
   "brier_b": 0.2601,
   "diff": 0.0124,
   "diff_sum": 0.1482,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "gemini",
   "b": "qwen",
   "brier_a": 0.2725,
   "brier_b": 0.1993,
   "diff": 0.0732,
   "diff_sum": 0.8781,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "gemini",
   "b": "zai",
   "brier_a": 0.2725,
   "brier_b": 0.2543,
   "diff": 0.0181,
   "diff_sum": 0.2175,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "grok",
   "b": "kimi",
   "brier_a": 0.2639,
   "brier_b": 0.2824,
   "diff": -0.0185,
   "diff_sum": -0.2214,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "grok",
   "b": "meta",
   "brier_a": 0.2639,
   "brier_b": 0.2636,
   "diff": 0.0003,
   "diff_sum": 0.004,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "grok",
   "b": "mimo",
   "brier_a": 0.2639,
   "brier_b": 0.2601,
   "diff": 0.0038,
   "diff_sum": 0.0457,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "grok",
   "b": "qwen",
   "brier_a": 0.2639,
   "brier_b": 0.1993,
   "diff": 0.0646,
   "diff_sum": 0.7756,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "grok",
   "b": "zai",
   "brier_a": 0.2639,
   "brier_b": 0.2543,
   "diff": 0.0096,
   "diff_sum": 0.115,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "kimi",
   "b": "meta",
   "brier_a": 0.2824,
   "brier_b": 0.2636,
   "diff": 0.0188,
   "diff_sum": 0.2254,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "kimi",
   "b": "mimo",
   "brier_a": 0.2824,
   "brier_b": 0.2601,
   "diff": 0.0223,
   "diff_sum": 0.2671,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "kimi",
   "b": "qwen",
   "brier_a": 0.2824,
   "brier_b": 0.1993,
   "diff": 0.0831,
   "diff_sum": 0.997,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "kimi",
   "b": "zai",
   "brier_a": 0.2824,
   "brier_b": 0.2543,
   "diff": 0.028,
   "diff_sum": 0.3364,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "meta",
   "b": "mimo",
   "brier_a": 0.2636,
   "brier_b": 0.2601,
   "diff": 0.0035,
   "diff_sum": 0.0417,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "meta",
   "b": "qwen",
   "brier_a": 0.2636,
   "brier_b": 0.1993,
   "diff": 0.0643,
   "diff_sum": 0.7716,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "meta",
   "b": "zai",
   "brier_a": 0.2636,
   "brier_b": 0.2543,
   "diff": 0.0093,
   "diff_sum": 0.111,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "mimo",
   "b": "qwen",
   "brier_a": 0.2601,
   "brier_b": 0.1993,
   "diff": 0.0608,
   "diff_sum": 0.7299,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "mimo",
   "b": "zai",
   "brier_a": 0.2601,
   "brier_b": 0.2543,
   "diff": 0.0058,
   "diff_sum": 0.0693,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "qwen",
   "b": "zai",
   "brier_a": 0.1993,
   "brier_b": 0.2543,
   "diff": -0.0551,
   "diff_sum": -0.6606,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "model_pair",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.2837,
   "brier_b": 0.25,
   "diff": 0.0337,
   "diff_sum": 0.370754,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2837,
   "brier_b": 0.25,
   "diff": 0.0337,
   "diff_sum": 0.370754,
   "event_ids": [
    "ev1-0135f4c5dcfc1e1c",
    "ev1-05d03c181d70f84b",
    "ev1-2194c4a5adf48e55",
    "ev1-340c0e34ae38de4b",
    "ev1-388c4547ac080115",
    "ev1-3cc8b8368fd4dbfd",
    "ev1-48bb15f32e8411b8",
    "ev1-94ee02cb6261edbc",
    "ev1-b53c9e96b8455573",
    "ev1-e68ca0097cb13f4a",
    "ev1-f18b9ef81c0a70bb"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m1",
   "n": 11,
   "session": "2026-10-19"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.2824,
   "brier_b": 0.25,
   "diff": 0.0324,
   "diff_sum": 0.38869,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m2",
   "n": 12,
   "session": "2026-10-20"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2824,
   "brier_b": 0.2369,
   "diff": 0.0455,
   "diff_sum": 0.545715,
   "event_ids": [
    "ev1-489c79176ee2dd15",
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-bc1eafcd5483b6e3",
    "ev1-c3231ab1f172f462",
    "ev1-d0dd2455c659f319",
    "ev1-d26b6668f17cb434",
    "ev1-f0ab585796c4cc1b"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m2",
   "n": 12,
   "session": "2026-10-20"
  },
  {
   "a": "consensus",
   "b": "crowd",
   "brier_a": 0.256,
   "brier_b": 0.2361,
   "diff": 0.0199,
   "diff_sum": 0.159151,
   "event_ids": [
    "ev1-51dee40f8f414f63",
    "ev1-5202796f4fde96fa",
    "ev1-7502e65bcc586be7",
    "ev1-a420778a5040fc40",
    "ev1-ac5f90505a7279ef",
    "ev1-b7f50239bd3df4b8",
    "ev1-c3231ab1f172f462",
    "ev1-d26b6668f17cb434"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m2",
   "n": 8,
   "session": "2026-10-20"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.226,
   "brier_b": 0.25,
   "diff": -0.024,
   "diff_sum": -0.287876,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-07a4ad7cba075157",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m3",
   "n": 12,
   "session": "2026-10-21"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2229,
   "brier_b": 0.2124,
   "diff": 0.0105,
   "diff_sum": 0.11554,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-11f537deda110878",
    "ev1-3949e35da48947a4",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-4abed3abfd18b517",
    "ev1-715633807bff9228",
    "ev1-a0f2889c8d96f2f8",
    "ev1-c9330c714938b363",
    "ev1-ce44d5e3f24443d8",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m3",
   "n": 11,
   "session": "2026-10-21"
  },
  {
   "a": "consensus",
   "b": "crowd",
   "brier_a": 0.223,
   "brier_b": 0.1458,
   "diff": 0.0772,
   "diff_sum": 0.386128,
   "event_ids": [
    "ev1-007e72a8a6465956",
    "ev1-4a0c3ccfaa6eb8f8",
    "ev1-c9330c714938b363",
    "ev1-e41332372593e98c",
    "ev1-f95bde198869757a"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m3",
   "n": 5,
   "session": "2026-10-21"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.2158,
   "brier_b": 0.25,
   "diff": -0.0342,
   "diff_sum": -0.41052,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2158,
   "brier_b": 0.3452,
   "diff": -0.1294,
   "diff_sum": -1.552389,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-355de3950dee14f6",
    "ev1-38b056fc82608a28",
    "ev1-3dd3aa8289c28f92",
    "ev1-644899acb912975a",
    "ev1-795ee03dc307eedd",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-9fc6f64098b2ca66",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-22"
  },
  {
   "a": "consensus",
   "b": "crowd",
   "brier_a": 0.1839,
   "brier_b": 0.1194,
   "diff": 0.0644,
   "diff_sum": 0.45103,
   "event_ids": [
    "ev1-336a251ab2351cb5",
    "ev1-3dd3aa8289c28f92",
    "ev1-862262ff4c98773e",
    "ev1-9cda9a86da48ad13",
    "ev1-b4f4c6c9889bdfd5",
    "ev1-daa068db17f6e351",
    "ev1-eff6195d14fb3a17"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 7,
   "session": "2026-10-22"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.2407,
   "brier_b": 0.25,
   "diff": -0.0093,
   "diff_sum": -0.111965,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2407,
   "brier_b": 0.2446,
   "diff": -0.004,
   "diff_sum": -0.047692,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-2546a3aec24e0b28",
    "ev1-33f0d0de20a7d0f0",
    "ev1-43bd506e1503b7be",
    "ev1-63788c542b111563",
    "ev1-95f51e2e9424d208",
    "ev1-b2a1ae226132982c",
    "ev1-c670b591a3408193",
    "ev1-cdab298edeeb278b",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-23"
  },
  {
   "a": "consensus",
   "b": "crowd",
   "brier_a": 0.1878,
   "brier_b": 0.1304,
   "diff": 0.0573,
   "diff_sum": 0.286727,
   "event_ids": [
    "ev1-03f669d276bc8ec9",
    "ev1-1735549526e6ace5",
    "ev1-2207473ed7638159",
    "ev1-33f0d0de20a7d0f0",
    "ev1-f8bf6dda002dd556"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 5,
   "session": "2026-10-23"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.2411,
   "brier_b": 0.25,
   "diff": -0.0089,
   "diff_sum": -0.107106,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-26"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2449,
   "brier_b": 0.2292,
   "diff": 0.0157,
   "diff_sum": 0.17317,
   "event_ids": [
    "ev1-014cef60e9c9842a",
    "ev1-1bc3269edde6fcc0",
    "ev1-3f034c1a740a7dbf",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-b640682c19a82615",
    "ev1-c881e6253eafe7a2",
    "ev1-e7d2698adedbe9c7",
    "ev1-f5abae76dc9ff3bd",
    "ev1-f5e51582fd2d42c9",
    "ev1-f90234f2ee3199bd"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-26"
  },
  {
   "a": "consensus",
   "b": "crowd",
   "brier_a": 0.185,
   "brier_b": 0.0947,
   "diff": 0.0902,
   "diff_sum": 0.360996,
   "event_ids": [
    "ev1-464cc1142b2f5479",
    "ev1-57bd50a618ed2849",
    "ev1-8abbdce5cb5da0ca",
    "ev1-f5e51582fd2d42c9"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 4,
   "session": "2026-10-26"
  },
  {
   "a": "consensus",
   "b": "coin",
   "brier_a": 0.2524,
   "brier_b": 0.25,
   "diff": 0.0024,
   "diff_sum": 0.02903,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-989299a74054570b",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 12,
   "session": "2026-10-27"
  },
  {
   "a": "consensus",
   "b": "climatology",
   "brier_a": 0.2543,
   "brier_b": 0.2346,
   "diff": 0.0197,
   "diff_sum": 0.216668,
   "event_ids": [
    "ev1-063b2e328305b39f",
    "ev1-11a3b0208e4270cf",
    "ev1-39fb687a76194c30",
    "ev1-5e9b9926e920295e",
    "ev1-73305bc56ed996e1",
    "ev1-80eaf06b3c1ea350",
    "ev1-93101a3a7bfa25a2",
    "ev1-9322a2719ecaaf82",
    "ev1-a08c0c836c788473",
    "ev1-ba9b574ce5d1462e",
    "ev1-d5ec5740731b8655"
   ],
   "kind": "consensus_vs_baseline",
   "methodology_version": "m4",
   "n": 11,
   "session": "2026-10-27"
  }
 ],
 "snapshot_id": "d7370f2e18a11024e371f0edff927c98ceb04ad9e82beca4b92176592a21aded",
 "snapshot_run": "2026-10-27-am",
 "unit": "session",
 "version": 1,
 "what": "one row = one session and one pair of models: n cells both counted on the same event (own-reference answers left out), the mean Brier of each, diff = brier_a - brier_b (below 0: a is better), diff_sum = the sum of the cell differences. The pooled mean difference of a pair = sum(diff_sum) / sum(n); its interval is drawn by whole sessions. №468: event_ids = the ids of the events of the row's cells (separated by ;); kind consensus_vs_baseline: a = consensus (the mean stated probability of the cell), b = coin (50%) / climatology (share of up before the session) / crowd (Polymarket, else Kalshi; its own question and outcome: a = the models' mean answer to the crowd's question)"
}