{
 "as_of": "2026-09-24T03:36:55Z",
 "axes": [
  "accountability",
  "affect",
  "agi",
  "art5",
  "asi",
  "care",
  "continuity",
  "creativity",
  "defence-aukus",
  "det",
  "efficiency",
  "fairness",
  "gov",
  "human-vs-ai",
  "jail",
  "jail-v2",
  "jail-v2-candidates",
  "mach",
  "mcp",
  "oss",
  "prv",
  "safety",
  "slot15",
  "sovereignty",
  "swarm",
  "swarm-candidates",
  "transparency",
  "xr"
 ],
 "axis_meta": {
  "accountability": {
   "decided_games": 34,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 8
  },
  "affect": {
   "decided_games": 41,
   "models_below_min_games": 0,
   "models_ranked": 6,
   "models_seen": 6,
   "ties": 125
  },
  "agi": {
   "decided_games": 1,
   "models_below_min_games": 2,
   "models_ranked": 0,
   "models_seen": 2,
   "ties": 156
  },
  "art5": {
   "decided_games": 32,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 85
  },
  "asi": {
   "decided_games": 43,
   "models_below_min_games": 2,
   "models_ranked": 5,
   "models_seen": 7,
   "ties": 106
  },
  "care": {
   "decided_games": 10,
   "models_below_min_games": 6,
   "models_ranked": 1,
   "models_seen": 7,
   "ties": 58
  },
  "continuity": {
   "decided_games": 58,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 16
  },
  "creativity": {
   "decided_games": 48,
   "models_below_min_games": 1,
   "models_ranked": 5,
   "models_seen": 6,
   "ties": 11
  },
  "defence-aukus": {
   "decided_games": 15,
   "models_below_min_games": 2,
   "models_ranked": 3,
   "models_seen": 5,
   "ties": 26
  },
  "det": {
   "decided_games": 30,
   "models_below_min_games": 0,
   "models_ranked": 2,
   "models_seen": 2,
   "ties": 89
  },
  "efficiency": {
   "decided_games": 57,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 12
  },
  "fairness": {
   "decided_games": 52,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 19
  },
  "gov": {
   "decided_games": 208,
   "models_below_min_games": 0,
   "models_ranked": 7,
   "models_seen": 7,
   "ties": 99
  },
  "human-vs-ai": {
   "decided_games": 49,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 16
  },
  "jail": {
   "decided_games": 0,
   "models_below_min_games": 0,
   "models_ranked": 0,
   "models_seen": 0,
   "ties": 138
  },
  "jail-v2": {
   "decided_games": 0,
   "models_below_min_games": 0,
   "models_ranked": 0,
   "models_seen": 0,
   "ties": 62
  },
  "jail-v2-candidates": {
   "decided_games": 0,
   "models_below_min_games": 0,
   "models_ranked": 0,
   "models_seen": 0,
   "ties": 70
  },
  "mach": {
   "decided_games": 33,
   "models_below_min_games": 0,
   "models_ranked": 6,
   "models_seen": 6,
   "ties": 66
  },
  "mcp": {
   "decided_games": 5,
   "models_below_min_games": 5,
   "models_ranked": 0,
   "models_seen": 5,
   "ties": 58
  },
  "oss": {
   "decided_games": 18,
   "models_below_min_games": 3,
   "models_ranked": 4,
   "models_seen": 7,
   "ties": 87
  },
  "prv": {
   "decided_games": 12,
   "models_below_min_games": 0,
   "models_ranked": 4,
   "models_seen": 4,
   "ties": 137
  },
  "safety": {
   "decided_games": 43,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 21
  },
  "slot15": {
   "decided_games": 45,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 18
  },
  "sovereignty": {
   "decided_games": 38,
   "models_below_min_games": 1,
   "models_ranked": 4,
   "models_seen": 5,
   "ties": 21
  },
  "swarm": {
   "decided_games": 18,
   "models_below_min_games": 2,
   "models_ranked": 3,
   "models_seen": 5,
   "ties": 46
  },
  "swarm-candidates": {
   "decided_games": 20,
   "models_below_min_games": 1,
   "models_ranked": 4,
   "models_seen": 5,
   "ties": 47
  },
  "transparency": {
   "decided_games": 51,
   "models_below_min_games": 0,
   "models_ranked": 5,
   "models_seen": 5,
   "ties": 14
  },
  "xr": {
   "decided_games": 20,
   "models_below_min_games": 1,
   "models_ranked": 2,
   "models_seen": 3,
   "ties": 91
  }
 },
 "content_id": "e35b71656d87f5bf01f59d45beab4107784b29e8ea4a9e436899c7708d8e232d",
 "generated": "2026-09-24T03:36:56Z",
 "leaderboard": [
  {
   "ci": [
    0.63,
    0.754
   ],
   "elo": 1660.6,
   "games": 210,
   "model": "qwen3:8b",
   "winrate": 0.695
  },
  {
   "ci": [
    0.359,
    0.666
   ],
   "elo": 1589.3,
   "games": 37,
   "model": "llama3.1:8b",
   "winrate": 0.514
  },
  {
   "ci": [
    0.465,
    0.638
   ],
   "elo": 1549.3,
   "games": 123,
   "model": "phi3.5:3.8b",
   "winrate": 0.553
  },
  {
   "ci": [
    0.507,
    0.617
   ],
   "elo": 1527.3,
   "games": 309,
   "model": "phi4:14b",
   "winrate": 0.563
  },
  {
   "ci": [
    0.414,
    0.525
   ],
   "elo": 1389.6,
   "games": 305,
   "model": "nemotron-3-nano:30b",
   "winrate": 0.469
  },
  {
   "ci": [
    0.221,
    0.299
   ],
   "elo": 1370.1,
   "games": 477,
   "model": "gemma3:12b",
   "winrate": 0.258
  },
  {
   "ci": [
    0.57,
    0.655
   ],
   "elo": 1365.1,
   "games": 494,
   "model": "mistral:7b",
   "winrate": 0.613
  }
 ],
 "method": "Bradley-Terry Elo, K=32, base 1500, per-axis and overall; Wilson 95% CI on win-rate; ranked only with n>=5 decided games; ties counted, not rated; style_controlled_weight honoured when a round carries it.",
 "models": 7,
 "n_rounds": 2683,
 "per_axis": {
  "accountability": [
   {
    "axis": "accountability",
    "ci": [
     0.548,
     0.93
    ],
    "elo": 1582.5,
    "games": 15,
    "model": "mistral:7b",
    "winrate": 0.8
   },
   {
    "axis": "accountability",
    "ci": [
     0.505,
     0.898
    ],
    "elo": 1580.7,
    "games": 16,
    "model": "phi4:14b",
    "winrate": 0.75
   },
   {
    "axis": "accountability",
    "ci": [
     0.566,
     1
    ],
    "elo": 1573.6,
    "games": 5,
    "model": "qwen3:8b",
    "winrate": 1
   },
   {
    "axis": "accountability",
    "ci": [
     0.109,
     0.52
    ],
    "elo": 1431.2,
    "games": 15,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.267
   },
   {
    "axis": "accountability",
    "ci": [
     0.01,
     0.27
    ],
    "elo": 1331.9,
    "games": 17,
    "model": "gemma3:12b",
    "winrate": 0.059
   }
  ],
  "affect": [
   {
    "axis": "affect",
    "ci": [
     0.565,
     0.98
    ],
    "elo": 1584.8,
    "games": 9,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.889
   },
   {
    "axis": "affect",
    "ci": [
     0.449,
     0.812
    ],
    "elo": 1549.9,
    "games": 23,
    "model": "phi3.5:3.8b",
    "winrate": 0.652
   },
   {
    "axis": "affect",
    "ci": [
     0.3,
     0.903
    ],
    "elo": 1525.7,
    "games": 6,
    "model": "qwen3:8b",
    "winrate": 0.667
   },
   {
    "axis": "affect",
    "ci": [
     0.137,
     0.694
    ],
    "elo": 1474.7,
    "games": 8,
    "model": "gemma3:12b",
    "winrate": 0.375
   },
   {
    "axis": "affect",
    "ci": [
     0.063,
     0.547
    ],
    "elo": 1449.1,
    "games": 9,
    "model": "phi4:14b",
    "winrate": 0.222
   },
   {
    "axis": "affect",
    "ci": [
     0.186,
     0.522
    ],
    "elo": 1415.7,
    "games": 27,
    "model": "mistral:7b",
    "winrate": 0.333
   }
  ],
  "agi": [],
  "art5": [
   {
    "axis": "art5",
    "ci": [
     0.621,
     0.963
    ],
    "elo": 1631.2,
    "games": 15,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.867
   },
   {
    "axis": "art5",
    "ci": [
     0.359,
     0.918
    ],
    "elo": 1546,
    "games": 7,
    "model": "mistral:7b",
    "winrate": 0.714
   },
   {
    "axis": "art5",
    "ci": [
     0.413,
     0.827
    ],
    "elo": 1536.4,
    "games": 17,
    "model": "gemma3:12b",
    "winrate": 0.647
   },
   {
    "axis": "art5",
    "ci": [
     0.082,
     0.641
    ],
    "elo": 1451.2,
    "games": 7,
    "model": "qwen3:8b",
    "winrate": 0.286
   },
   {
    "axis": "art5",
    "ci": [
     0.01,
     0.258
    ],
    "elo": 1335.3,
    "games": 18,
    "model": "phi4:14b",
    "winrate": 0.056
   }
  ],
  "asi": [
   {
    "axis": "asi",
    "ci": [
     0.3,
     0.903
    ],
    "elo": 1527.2,
    "games": 6,
    "model": "phi4:14b",
    "winrate": 0.667
   },
   {
    "axis": "asi",
    "ci": [
     0.28,
     0.72
    ],
    "elo": 1510.1,
    "games": 16,
    "model": "qwen3:8b",
    "winrate": 0.5
   },
   {
    "axis": "asi",
    "ci": [
     0.245,
     0.635
    ],
    "elo": 1509.7,
    "games": 21,
    "model": "phi3.5:3.8b",
    "winrate": 0.429
   },
   {
    "axis": "asi",
    "ci": [
     0.388,
     0.755
    ],
    "elo": 1509.6,
    "games": 24,
    "model": "mistral:7b",
    "winrate": 0.583
   },
   {
    "axis": "asi",
    "ci": [
     0.248,
     0.699
    ],
    "elo": 1473.9,
    "games": 15,
    "model": "llama3.1:8b",
    "winrate": 0.467
   }
  ],
  "care": [
   {
    "axis": "care",
    "ci": [
     0.231,
     0.882
    ],
    "elo": 1519.3,
    "games": 5,
    "model": "mistral:7b",
    "winrate": 0.6
   }
  ],
  "continuity": [
   {
    "axis": "continuity",
    "ci": [
     0.653,
     0.936
    ],
    "elo": 1667.8,
    "games": 25,
    "model": "mistral:7b",
    "winrate": 0.84
   },
   {
    "axis": "continuity",
    "ci": [
     0.529,
     0.847
    ],
    "elo": 1593.6,
    "games": 28,
    "model": "phi4:14b",
    "winrate": 0.714
   },
   {
    "axis": "continuity",
    "ci": [
     0.359,
     0.918
    ],
    "elo": 1523,
    "games": 7,
    "model": "qwen3:8b",
    "winrate": 0.714
   },
   {
    "axis": "continuity",
    "ci": [
     0.255,
     0.593
    ],
    "elo": 1456.9,
    "games": 29,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.414
   },
   {
    "axis": "continuity",
    "ci": [
     0,
     0.125
    ],
    "elo": 1258.8,
    "games": 27,
    "model": "gemma3:12b",
    "winrate": 0
   }
  ],
  "creativity": [
   {
    "axis": "creativity",
    "ci": [
     0.552,
     0.953
    ],
    "elo": 1606.2,
    "games": 12,
    "model": "qwen3:8b",
    "winrate": 0.833
   },
   {
    "axis": "creativity",
    "ci": [
     0.5,
     0.862
    ],
    "elo": 1598.7,
    "games": 21,
    "model": "mistral:7b",
    "winrate": 0.714
   },
   {
    "axis": "creativity",
    "ci": [
     0.321,
     0.679
    ],
    "elo": 1468.9,
    "games": 26,
    "model": "phi4:14b",
    "winrate": 0.5
   },
   {
    "axis": "creativity",
    "ci": [
     0.173,
     0.587
    ],
    "elo": 1457.3,
    "games": 17,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.353
   },
   {
    "axis": "creativity",
    "ci": [
     0.055,
     0.376
    ],
    "elo": 1352.9,
    "games": 19,
    "model": "gemma3:12b",
    "winrate": 0.158
   }
  ],
  "defence-aukus": [
   {
    "axis": "defence-aukus",
    "ci": [
     0.529,
     0.978
    ],
    "elo": 1570.1,
    "games": 8,
    "model": "mistral:7b",
    "winrate": 0.875
   },
   {
    "axis": "defence-aukus",
    "ci": [
     0.03,
     0.564
    ],
    "elo": 1446.4,
    "games": 6,
    "model": "gemma3:12b",
    "winrate": 0.167
   },
   {
    "axis": "defence-aukus",
    "ci": [
     0,
     0.299
    ],
    "elo": 1386.6,
    "games": 9,
    "model": "phi4:14b",
    "winrate": 0
   }
  ],
  "det": [
   {
    "axis": "det",
    "ci": [
     0.488,
     0.808
    ],
    "elo": 1580.1,
    "games": 30,
    "model": "qwen3:8b",
    "winrate": 0.667
   },
   {
    "axis": "det",
    "ci": [
     0.192,
     0.512
    ],
    "elo": 1419.9,
    "games": 30,
    "model": "phi3.5:3.8b",
    "winrate": 0.333
   }
  ],
  "efficiency": [
   {
    "axis": "efficiency",
    "ci": [
     0.549,
     0.894
    ],
    "elo": 1597.8,
    "games": 21,
    "model": "mistral:7b",
    "winrate": 0.762
   },
   {
    "axis": "efficiency",
    "ci": [
     0.469,
     0.867
    ],
    "elo": 1556.9,
    "games": 17,
    "model": "qwen3:8b",
    "winrate": 0.706
   },
   {
    "axis": "efficiency",
    "ci": [
     0.454,
     0.828
    ],
    "elo": 1551.4,
    "games": 21,
    "model": "phi4:14b",
    "winrate": 0.667
   },
   {
    "axis": "efficiency",
    "ci": [
     0.43,
     0.803
    ],
    "elo": 1551.3,
    "games": 22,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.636
   },
   {
    "axis": "efficiency",
    "ci": [
     0.005,
     0.153
    ],
    "elo": 1242.5,
    "games": 33,
    "model": "gemma3:12b",
    "winrate": 0.03
   }
  ],
  "fairness": [
   {
    "axis": "fairness",
    "ci": [
     0.595,
     0.908
    ],
    "elo": 1622.6,
    "games": 24,
    "model": "mistral:7b",
    "winrate": 0.792
   },
   {
    "axis": "fairness",
    "ci": [
     0.481,
     0.855
    ],
    "elo": 1592.9,
    "games": 20,
    "model": "phi4:14b",
    "winrate": 0.7
   },
   {
    "axis": "fairness",
    "ci": [
     0.397,
     0.892
    ],
    "elo": 1548.9,
    "games": 10,
    "model": "qwen3:8b",
    "winrate": 0.7
   },
   {
    "axis": "fairness",
    "ci": [
     0.192,
     0.512
    ],
    "elo": 1397.5,
    "games": 30,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.333
   },
   {
    "axis": "fairness",
    "ci": [
     0.028,
     0.301
    ],
    "elo": 1338.1,
    "games": 20,
    "model": "gemma3:12b",
    "winrate": 0.1
   }
  ],
  "gov": [
   {
    "axis": "gov",
    "ci": [
     0.535,
     0.875
    ],
    "elo": 1616.3,
    "games": 23,
    "model": "phi3.5:3.8b",
    "winrate": 0.739
   },
   {
    "axis": "gov",
    "ci": [
     0.424,
     0.873
    ],
    "elo": 1564.6,
    "games": 13,
    "model": "qwen3:8b",
    "winrate": 0.692
   },
   {
    "axis": "gov",
    "ci": [
     0.46,
     0.846
    ],
    "elo": 1555.7,
    "games": 19,
    "model": "phi4:14b",
    "winrate": 0.684
   },
   {
    "axis": "gov",
    "ci": [
     0.433,
     0.578
    ],
    "elo": 1475.5,
    "games": 180,
    "model": "mistral:7b",
    "winrate": 0.506
   },
   {
    "axis": "gov",
    "ci": [
     0.168,
     0.687
    ],
    "elo": 1475.4,
    "games": 10,
    "model": "llama3.1:8b",
    "winrate": 0.4
   },
   {
    "axis": "gov",
    "ci": [
     0.379,
     0.533
    ],
    "elo": 1410.8,
    "games": 156,
    "model": "gemma3:12b",
    "winrate": 0.455
   },
   {
    "axis": "gov",
    "ci": [
     0.07,
     0.452
    ],
    "elo": 1401.7,
    "games": 15,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.2
   }
  ],
  "human-vs-ai": [
   {
    "axis": "human-vs-ai",
    "ci": [
     0.584,
     0.919
    ],
    "elo": 1604.2,
    "games": 20,
    "model": "mistral:7b",
    "winrate": 0.8
   },
   {
    "axis": "human-vs-ai",
    "ci": [
     0.454,
     0.828
    ],
    "elo": 1565.9,
    "games": 21,
    "model": "phi4:14b",
    "winrate": 0.667
   },
   {
    "axis": "human-vs-ai",
    "ci": [
     0.397,
     0.892
    ],
    "elo": 1561.6,
    "games": 10,
    "model": "qwen3:8b",
    "winrate": 0.7
   },
   {
    "axis": "human-vs-ai",
    "ci": [
     0.236,
     0.576
    ],
    "elo": 1447.6,
    "games": 28,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.393
   },
   {
    "axis": "human-vs-ai",
    "ci": [
     0.009,
     0.246
    ],
    "elo": 1320.7,
    "games": 19,
    "model": "gemma3:12b",
    "winrate": 0.053
   }
  ],
  "jail": [],
  "jail-v2": [],
  "jail-v2-candidates": [],
  "mach": [
   {
    "axis": "mach",
    "ci": [
     0.505,
     0.898
    ],
    "elo": 1592.4,
    "games": 16,
    "model": "phi4:14b",
    "winrate": 0.75
   },
   {
    "axis": "mach",
    "ci": [
     0.566,
     1
    ],
    "elo": 1568.3,
    "games": 5,
    "model": "llama3.1:8b",
    "winrate": 1
   },
   {
    "axis": "mach",
    "ci": [
     0.189,
     0.733
    ],
    "elo": 1501.9,
    "games": 9,
    "model": "qwen3:8b",
    "winrate": 0.444
   },
   {
    "axis": "mach",
    "ci": [
     0.189,
     0.733
    ],
    "elo": 1481.2,
    "games": 9,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.444
   },
   {
    "axis": "mach",
    "ci": [
     0.185,
     0.614
    ],
    "elo": 1439.5,
    "games": 16,
    "model": "mistral:7b",
    "winrate": 0.375
   },
   {
    "axis": "mach",
    "ci": [
     0.051,
     0.477
    ],
    "elo": 1416.7,
    "games": 11,
    "model": "gemma3:12b",
    "winrate": 0.182
   }
  ],
  "mcp": [],
  "oss": [
   {
    "axis": "oss",
    "ci": [
     0.646,
     1
    ],
    "elo": 1588,
    "games": 7,
    "model": "qwen3:8b",
    "winrate": 1
   },
   {
    "axis": "oss",
    "ci": [
     0.3,
     0.903
    ],
    "elo": 1524.8,
    "games": 6,
    "model": "gemma3:12b",
    "winrate": 0.667
   },
   {
    "axis": "oss",
    "ci": [
     0.057,
     0.51
    ],
    "elo": 1426,
    "games": 10,
    "model": "mistral:7b",
    "winrate": 0.2
   },
   {
    "axis": "oss",
    "ci": [
     0.022,
     0.471
    ],
    "elo": 1417.3,
    "games": 8,
    "model": "phi4:14b",
    "winrate": 0.125
   }
  ],
  "prv": [
   {
    "axis": "prv",
    "ci": [
     0.436,
     0.97
    ],
    "elo": 1550.2,
    "games": 6,
    "model": "qwen3:8b",
    "winrate": 0.833
   },
   {
    "axis": "prv",
    "ci": [
     0.3,
     0.903
    ],
    "elo": 1515.7,
    "games": 6,
    "model": "phi3.5:3.8b",
    "winrate": 0.667
   },
   {
    "axis": "prv",
    "ci": [
     0.097,
     0.7
    ],
    "elo": 1484.3,
    "games": 6,
    "model": "llama3.1:8b",
    "winrate": 0.333
   },
   {
    "axis": "prv",
    "ci": [
     0.03,
     0.564
    ],
    "elo": 1449.8,
    "games": 6,
    "model": "gemma3:12b",
    "winrate": 0.167
   }
  ],
  "safety": [
   {
    "axis": "safety",
    "ci": [
     0.57,
     0.934
    ],
    "elo": 1601.6,
    "games": 16,
    "model": "mistral:7b",
    "winrate": 0.812
   },
   {
    "axis": "safety",
    "ci": [
     0.505,
     0.898
    ],
    "elo": 1594,
    "games": 16,
    "model": "qwen3:8b",
    "winrate": 0.75
   },
   {
    "axis": "safety",
    "ci": [
     0.214,
     0.674
    ],
    "elo": 1484.8,
    "games": 14,
    "model": "phi4:14b",
    "winrate": 0.429
   },
   {
    "axis": "safety",
    "ci": [
     0.222,
     0.592
    ],
    "elo": 1433.3,
    "games": 23,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.391
   },
   {
    "axis": "safety",
    "ci": [
     0.062,
     0.41
    ],
    "elo": 1386.2,
    "games": 17,
    "model": "gemma3:12b",
    "winrate": 0.176
   }
  ],
  "slot15": [
   {
    "axis": "slot15",
    "ci": [
     0.641,
     0.933
    ],
    "elo": 1630.8,
    "games": 24,
    "model": "mistral:7b",
    "winrate": 0.833
   },
   {
    "axis": "slot15",
    "ci": [
     0.596,
     0.982
    ],
    "elo": 1607.7,
    "games": 10,
    "model": "qwen3:8b",
    "winrate": 0.9
   },
   {
    "axis": "slot15",
    "ci": [
     0.246,
     0.663
    ],
    "elo": 1485.6,
    "games": 18,
    "model": "phi4:14b",
    "winrate": 0.444
   },
   {
    "axis": "slot15",
    "ci": [
     0.125,
     0.509
    ],
    "elo": 1406.4,
    "games": 18,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.278
   },
   {
    "axis": "slot15",
    "ci": [
     0.052,
     0.36
    ],
    "elo": 1369.6,
    "games": 20,
    "model": "gemma3:12b",
    "winrate": 0.15
   }
  ],
  "sovereignty": [
   {
    "axis": "sovereignty",
    "ci": [
     0.7,
     0.958
    ],
    "elo": 1628.5,
    "games": 25,
    "model": "phi4:14b",
    "winrate": 0.88
   },
   {
    "axis": "sovereignty",
    "ci": [
     0.565,
     0.98
    ],
    "elo": 1582.2,
    "games": 9,
    "model": "mistral:7b",
    "winrate": 0.889
   },
   {
    "axis": "sovereignty",
    "ci": [
     0.076,
     0.476
    ],
    "elo": 1412,
    "games": 14,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.214
   },
   {
    "axis": "sovereignty",
    "ci": [
     0.007,
     0.202
    ],
    "elo": 1321.1,
    "games": 24,
    "model": "gemma3:12b",
    "winrate": 0.042
   }
  ],
  "swarm": [
   {
    "axis": "swarm",
    "ci": [
     0.796,
     1
    ],
    "elo": 1662.7,
    "games": 15,
    "model": "nemotron-3-nano:30b",
    "winrate": 1
   },
   {
    "axis": "swarm",
    "ci": [
     0.026,
     0.513
    ],
    "elo": 1454.6,
    "games": 7,
    "model": "gemma3:12b",
    "winrate": 0.143
   },
   {
    "axis": "swarm",
    "ci": [
     0.02,
     0.435
    ],
    "elo": 1433.7,
    "games": 9,
    "model": "mistral:7b",
    "winrate": 0.111
   }
  ],
  "swarm-candidates": [
   {
    "axis": "swarm-candidates",
    "ci": [
     0.306,
     0.863
    ],
    "elo": 1525.4,
    "games": 8,
    "model": "mistral:7b",
    "winrate": 0.625
   },
   {
    "axis": "swarm-candidates",
    "ci": [
     0.291,
     0.768
    ],
    "elo": 1520.2,
    "games": 13,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.538
   },
   {
    "axis": "swarm-candidates",
    "ci": [
     0.215,
     0.785
    ],
    "elo": 1503.2,
    "games": 8,
    "model": "gemma3:12b",
    "winrate": 0.5
   },
   {
    "axis": "swarm-candidates",
    "ci": [
     0.082,
     0.641
    ],
    "elo": 1455.4,
    "games": 7,
    "model": "phi4:14b",
    "winrate": 0.286
   }
  ],
  "transparency": [
   {
    "axis": "transparency",
    "ci": [
     0.641,
     0.933
    ],
    "elo": 1673,
    "games": 24,
    "model": "mistral:7b",
    "winrate": 0.833
   },
   {
    "axis": "transparency",
    "ci": [
     0.468,
     0.911
    ],
    "elo": 1562.4,
    "games": 12,
    "model": "qwen3:8b",
    "winrate": 0.75
   },
   {
    "axis": "transparency",
    "ci": [
     0.342,
     0.742
    ],
    "elo": 1496,
    "games": 20,
    "model": "phi4:14b",
    "winrate": 0.55
   },
   {
    "axis": "transparency",
    "ci": [
     0.219,
     0.613
    ],
    "elo": 1445.1,
    "games": 20,
    "model": "nemotron-3-nano:30b",
    "winrate": 0.4
   },
   {
    "axis": "transparency",
    "ci": [
     0.04,
     0.29
    ],
    "elo": 1323.6,
    "games": 26,
    "model": "gemma3:12b",
    "winrate": 0.115
   }
  ],
  "xr": [
   {
    "axis": "xr",
    "ci": [
     0.46,
     0.846
    ],
    "elo": 1534.9,
    "games": 19,
    "model": "phi3.5:3.8b",
    "winrate": 0.684
   },
   {
    "axis": "xr",
    "ci": [
     0.145,
     0.519
    ],
    "elo": 1449.1,
    "games": 20,
    "model": "gemma3:12b",
    "winrate": 0.3
   }
  ]
 },
 "rank_rule": "leader named on an axis only when >=2 ranked models and the top model's Wilson 95% win-rate CI lower bound exceeds the runner-up's upper bound; otherwise TIE (ranked, not separated).",
 "register": "MEASURED for a ranked row (n>=5 decided games, deterministic grader on the recorded rounds); an axis with no ranked row is UNMEASURED: not sufficient to rank. Measurement, not certification.",
 "rounds": {
  "decided": 981,
  "style_weighted_rounds": 0,
  "ties": 1702,
  "unusable": 0
 },
 "schema": "csoai.arena-elo-reference/0.2",
 "signature": {
  "alg": "Ed25519",
  "canonical": "JSON.stringify of key-sorted object, UTF-8; int-valued floats as ints (functions/_lib/cardSign.ts canonicalBytes)",
  "did": "did:web:csoai.org#board-attestation-1",
  "envelope": {
   "content_id": "e35b71656d87f5bf01f59d45beab4107784b29e8ea4a9e436899c7708d8e232d",
   "generated": "2026-09-24T03:36:56Z",
   "n_rounds": 2683,
   "not_a_grade": "A signature proves these bytes were signed by the board key; it proves no claim inside them beyond what the recorded rounds measured.",
   "schema": "csoai.arena-elo-reference-attestation/0.1",
   "signer": "did:web:csoai.org#board-attestation-1 via POST /api/board-sign (pod caller token)",
   "sources": [
    {
     "path": "public/arena/rounds.jsonl",
     "rounds": 2683,
     "sha256": "fc47cf93194169cf10fd592fb9a5a759e741a3e2efa998c002b3c5e87d2505de"
    }
   ]
  },
  "payload_sha256": "fe451bb127fa8ac6955b0a7ed09395887de9cb6f00fd1bc370ff273980dc691c",
  "preimage": "canonical(envelope); envelope.content_id == sha256(canonical(body minus content_id, signature))",
  "sig_ed25519": "0c2ae7dde22ad6ffef654946b4bf0f4fa792eb0f47c341f7cd36273cfd4f4d59951a3152436337c85395d1b8da3753cb2621356e1d71bb50605844d048484e08",
  "signed_at": "2026-09-24T03:36:57.005Z",
  "signer_auth": "pod-token",
  "verify": "sha256(canonical preimage) == payload_sha256; Ed25519 verify sig_ed25519 (hex) over the canonical preimage bytes with the #board-attestation-1 key in https://csoai.org/.well-known/did.json"
 },
 "sources": [
  {
   "path": "public/arena/rounds.jsonl",
   "rounds": 2683,
   "sha256": "fc47cf93194169cf10fd592fb9a5a759e741a3e2efa998c002b3c5e87d2505de",
   "unparsable_lines": 0
  }
 ],
 "supersedes": {
  "content_id": "165b28abe7beeeb83a2044131b8dab96775892769793d0e022fd7c0c5279d82e",
  "generated": "2026-09-24T02:37:27Z",
  "note": "previous file superseded, never edited",
  "signer": "did:web:csoai.org#board-attestation-1"
 }
}
