{ "kind": "system-one-arena-leagues", "note": "Engine summaries (matches/summary.mjs) of the arena league recordings. Fair-mode leagues (ids ending in @N) apply the same simulated answer latency of N ms to every player; the call times in them are the real measured ones. Elo: K 32, 200 seeded orders, 95% bootstrap intervals.", "leagues": [ { "id": "othello", "files": [ "othello-s1.jsonl" ], "matches": 144, "engine": "matches/1", "settings": { "elo": { "k": 32, "shuffles": 200, "bootstrapResamples": 200, "seed": 1, "start": 1000, "note": "mean of sequential Elo over seeded shuffles of all games; 95% interval from bootstrap over games" } }, "games": { "othello": { "matches": 144, "players": [ { "id": "perfect", "label": "perfect", "kind": "perfect", "games": 32, "wins": 32, "draws": 0, "losses": 0, "scorePct": 100, "elo": 1280, "eloCI95": [ 1220, 1326 ], "moves": 501, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 501, "count": 501, "rate": 1 }, "matchPerfectOnDecisive": { "n": 282, "count": 282, "rate": 1 }, "pointsFor": 1055, "pointsAgainst": 58 }, { "id": "clef", "label": "Clef 27B", "kind": "model", "games": 32, "wins": 20, "draws": 2, "losses": 10, "scorePct": 65.6, "elo": 1082, "eloCI95": [ 1009, 1156 ], "moves": 431, "modelMoves": 431, "fallbackRate": { "n": 431, "count": 0, "rate": 0 }, "illegalRate": { "n": 431, "count": 0, "rate": 0 }, "errorRate": { "n": 431, "count": 0, "rate": 0 }, "latencyMs": { "n": 431, "mean": 3440.7, "median": 3047.1, "p95": 6088.9 }, "latencyIsolatedMs": { "n": 302, "mean": 2808.6, "median": 2731.6, "p95": 3574.4 }, "matchPerfect": { "n": 374, "count": 152, "rate": 0.4064 }, "matchPerfectOnDecisive": { "n": 319, "count": 97, "rate": 0.3041 }, "pointsFor": 562, "pointsAgainst": 574 }, { "id": "random", "label": "random", "kind": "random", "games": 32, "wins": 17, "draws": 0, "losses": 15, "scorePct": 53.1, "elo": 1015, "eloCI95": [ 902, 1106 ], "moves": 441, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 364, "count": 146, "rate": 0.4011 }, "matchPerfectOnDecisive": { "n": 308, "count": 90, "rate": 0.2922 }, "pointsFor": 517, "pointsAgainst": 627 }, { "id": "laya", "label": "Laya", "kind": "model", "games": 32, "wins": 15, "draws": 1, "losses": 16, "scorePct": 48.4, "elo": 990, "eloCI95": [ 908, 1072 ], "moves": 443, "modelMoves": 443, "fallbackRate": { "n": 443, "count": 0, "rate": 0 }, "illegalRate": { "n": 443, "count": 0, "rate": 0 }, "errorRate": { "n": 443, "count": 0, "rate": 0 }, "latencyMs": { "n": 443, "mean": 307.2, "median": 306.6, "p95": 550.3 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 379, "count": 153, "rate": 0.4037 }, "matchPerfectOnDecisive": { "n": 323, "count": 97, "rate": 0.3003 }, "pointsFor": 532, "pointsAgainst": 620 }, { "id": "julia-1", "label": "Julia-1", "kind": "model", "games": 32, "wins": 13, "draws": 2, "losses": 17, "scorePct": 43.8, "elo": 965, "eloCI95": [ 875, 1060 ], "moves": 437, "modelMoves": 437, "fallbackRate": { "n": 437, "count": 0, "rate": 0 }, "illegalRate": { "n": 437, "count": 0, "rate": 0 }, "errorRate": { "n": 437, "count": 0, "rate": 0 }, "latencyMs": { "n": 437, "mean": 164.4, "median": 153.7, "p95": 307.1 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 368, "count": 134, "rate": 0.3641 }, "matchPerfectOnDecisive": { "n": 314, "count": 80, "rate": 0.2548 }, "pointsFor": 503, "pointsAgainst": 632 }, { "id": "lev", "label": "lev 4B", "kind": "model", "games": 32, "wins": 14, "draws": 0, "losses": 18, "scorePct": 43.8, "elo": 964, "eloCI95": [ 888, 1055 ], "moves": 423, "modelMoves": 423, "fallbackRate": { "n": 423, "count": 0, "rate": 0 }, "illegalRate": { "n": 423, "count": 0, "rate": 0 }, "errorRate": { "n": 423, "count": 0, "rate": 0 }, "latencyMs": { "n": 423, "mean": 1727.2, "median": 1619.1, "p95": 2796.7 }, "latencyIsolatedMs": { "n": 20, "mean": 659, "median": 547.2, "p95": 1199.3 }, "matchPerfect": { "n": 352, "count": 117, "rate": 0.3324 }, "matchPerfectOnDecisive": { "n": 305, "count": 70, "rate": 0.2295 }, "pointsFor": 490, "pointsAgainst": 643 }, { "id": "clef-flash", "label": "Clef-Flash 9B", "kind": "model", "games": 32, "wins": 11, "draws": 1, "losses": 20, "scorePct": 35.9, "elo": 924, "eloCI95": [ 856, 1002 ], "moves": 435, "modelMoves": 435, "fallbackRate": { "n": 435, "count": 0, "rate": 0 }, "illegalRate": { "n": 435, "count": 0, "rate": 0 }, "errorRate": { "n": 435, "count": 0, "rate": 0 }, "latencyMs": { "n": 435, "mean": 1757.8, "median": 1785.9, "p95": 2606.6 }, "latencyIsolatedMs": { "n": 14, "mean": 887.9, "median": 828.4, "p95": 1376.6 }, "matchPerfect": { "n": 346, "count": 121, "rate": 0.3497 }, "matchPerfectOnDecisive": { "n": 300, "count": 75, "rate": 0.25 }, "pointsFor": 492, "pointsAgainst": 659 }, { "id": "kev-4b", "label": "Kev 4B", "kind": "model", "games": 32, "wins": 9, "draws": 1, "losses": 22, "scorePct": 29.7, "elo": 891, "eloCI95": [ 814, 991 ], "moves": 438, "modelMoves": 438, "fallbackRate": { "n": 438, "count": 0, "rate": 0 }, "illegalRate": { "n": 438, "count": 0, "rate": 0 }, "errorRate": { "n": 438, "count": 0, "rate": 0 }, "latencyMs": { "n": 438, "mean": 1040.7, "median": 873.7, "p95": 1884.8 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 352, "count": 98, "rate": 0.2784 }, "matchPerfectOnDecisive": { "n": 321, "count": 67, "rate": 0.2087 }, "pointsFor": 520, "pointsAgainst": 630 }, { "id": "jev", "label": "Jev 1.13", "kind": "model", "games": 32, "wins": 9, "draws": 1, "losses": 22, "scorePct": 29.7, "elo": 890, "eloCI95": [ 800, 972 ], "moves": 428, "modelMoves": 428, "fallbackRate": { "n": 428, "count": 0, "rate": 0 }, "illegalRate": { "n": 428, "count": 0, "rate": 0 }, "errorRate": { "n": 428, "count": 0, "rate": 0 }, "latencyMs": { "n": 428, "mean": 141.4, "median": 134.5, "p95": 197.2 }, "latencyIsolatedMs": { "n": 1, "mean": 124, "median": 124, "p95": 124 }, "matchPerfect": { "n": 338, "count": 110, "rate": 0.3254 }, "matchPerfectOnDecisive": { "n": 309, "count": 81, "rate": 0.2621 }, "pointsFor": 458, "pointsAgainst": 686 } ], "h2h": [ { "a": "clef-flash", "b": "jev", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "clef-flash", "b": "julia-1", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "clef-flash", "b": "kev-4b", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "clef-flash", "b": "laya", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "clef-flash", "b": "lev", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef-flash", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef-flash", "b": "random", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "clef", "b": "clef-flash", "games": 4, "aWins": 2, "bWins": 1, "draws": 1 }, { "a": "clef", "b": "jev", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "clef", "b": "julia-1", "games": 4, "aWins": 2, "bWins": 1, "draws": 1 }, { "a": "clef", "b": "kev-4b", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "clef", "b": "laya", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "clef", "b": "lev", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "clef", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef", "b": "random", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "jev", "b": "julia-1", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "jev", "b": "kev-4b", "games": 4, "aWins": 2, "bWins": 1, "draws": 1 }, { "a": "jev", "b": "laya", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "jev", "b": "lev", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "jev", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "jev", "b": "random", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "julia-1", "b": "kev-4b", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "julia-1", "b": "laya", "games": 4, "aWins": 1, "bWins": 2, "draws": 1 }, { "a": "julia-1", "b": "lev", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "julia-1", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "julia-1", "b": "random", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "kev-4b", "b": "laya", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "kev-4b", "b": "lev", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "kev-4b", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "kev-4b", "b": "random", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "laya", "b": "lev", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "laya", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "laya", "b": "random", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "lev", "b": "perfect", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "lev", "b": "random", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "perfect", "b": "random", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 } ] } } }, { "id": "pong-fair-featured", "files": [ "pong-fair-featured-clef-jev.jsonl", "pong-fair-featured-clef-clef-flash.jsonl", "pong-fair-featured-clef-perfect.jsonl" ], "matches": 3, "engine": "matches/1", "settings": { "elo": { "k": 32, "shuffles": 200, "bootstrapResamples": 200, "seed": 1, "start": 1000, "note": "mean of sequential Elo over seeded shuffles of all games; 95% interval from bootstrap over games" } }, "games": { "pong": { "matches": 3, "players": [ { "id": "perfect", "label": "perfect", "kind": "perfect", "games": 1, "wins": 1, "draws": 0, "losses": 0, "scorePct": 100, "elo": 1017, "eloCI95": [ 1016, 1044 ], "moves": 37, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 18, "count": 18, "rate": 1 }, "matchPerfectOnDecisive": { "n": 18, "count": 18, "rate": 1 }, "pointsFor": 3, "pointsAgainst": 1, "returns": 19, "misses": 1, "returnRate": { "n": 20, "count": 19, "rate": 0.95 } }, { "id": "clef@150", "label": "Clef 27B", "kind": "model", "games": 3, "wins": 2, "draws": 0, "losses": 1, "scorePct": 66.7, "elo": 1015, "eloCI95": [ 985, 1045 ], "moves": 337, "modelMoves": 337, "fallbackRate": { "n": 337, "count": 0, "rate": 0 }, "illegalRate": { "n": 337, "count": 0, "rate": 0 }, "errorRate": { "n": 337, "count": 0, "rate": 0 }, "latencyMs": { "n": 337, "mean": 1870.5, "median": 1857.9, "p95": 1995.3 }, "latencyIsolatedMs": { "n": 337, "mean": 1870.5, "median": 1857.9, "p95": 1995.3 }, "matchPerfect": { "n": 149, "count": 144, "rate": 0.9664 }, "matchPerfectOnDecisive": { "n": 149, "count": 144, "rate": 0.9664 }, "pointsFor": 7, "pointsAgainst": 5, "returns": 35, "misses": 5, "returnRate": { "n": 40, "count": 35, "rate": 0.875 } }, { "id": "jev@150", "label": "Jev 1.13", "kind": "model", "games": 1, "wins": 0, "draws": 0, "losses": 1, "scorePct": 0, "elo": 984, "eloCI95": [ 956, 985 ], "moves": 114, "modelMoves": 114, "fallbackRate": { "n": 114, "count": 0, "rate": 0 }, "illegalRate": { "n": 114, "count": 0, "rate": 0 }, "errorRate": { "n": 114, "count": 0, "rate": 0 }, "latencyMs": { "n": 114, "mean": 162.5, "median": 134.2, "p95": 176.4 }, "latencyIsolatedMs": { "n": 114, "mean": 162.5, "median": 134.2, "p95": 176.4 }, "matchPerfect": { "n": 52, "count": 52, "rate": 1 }, "matchPerfectOnDecisive": { "n": 52, "count": 52, "rate": 1 }, "pointsFor": 2, "pointsAgainst": 3, "returns": 9, "misses": 3, "returnRate": { "n": 12, "count": 9, "rate": 0.75 } }, { "id": "clef-flash@150", "label": "Clef-Flash 9B", "kind": "model", "games": 1, "wins": 0, "draws": 0, "losses": 1, "scorePct": 0, "elo": 984, "eloCI95": [ 956, 985 ], "moves": 66, "modelMoves": 66, "fallbackRate": { "n": 66, "count": 0, "rate": 0 }, "illegalRate": { "n": 66, "count": 0, "rate": 0 }, "errorRate": { "n": 66, "count": 0, "rate": 0 }, "latencyMs": { "n": 66, "mean": 566.7, "median": 567.8, "p95": 595.7 }, "latencyIsolatedMs": { "n": 66, "mean": 566.7, "median": 567.8, "p95": 595.7 }, "matchPerfect": { "n": 33, "count": 20, "rate": 0.6061 }, "matchPerfectOnDecisive": { "n": 33, "count": 20, "rate": 0.6061 }, "pointsFor": 0, "pointsAgainst": 3, "returns": 5, "misses": 3, "returnRate": { "n": 8, "count": 5, "rate": 0.625 } } ], "h2h": [ { "a": "clef-flash@150", "b": "clef@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "clef@150", "b": "jev@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "clef@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 } ] } } }, { "id": "pong-fair", "files": [ "pong-fair-s1.jsonl" ], "matches": 28, "engine": "matches/1", "settings": { "elo": { "k": 32, "shuffles": 200, "bootstrapResamples": 200, "seed": 1, "start": 1000, "note": "mean of sequential Elo over seeded shuffles of all games; 95% interval from bootstrap over games" } }, "games": { "pong": { "matches": 28, "players": [ { "id": "perfect", "label": "perfect", "kind": "perfect", "games": 7, "wins": 7, "draws": 0, "losses": 0, "scorePct": 100, "elo": 1098, "eloCI95": [ 1045, 1138 ], "moves": 69, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 31, "count": 31, "rate": 1 }, "matchPerfectOnDecisive": { "n": 31, "count": 31, "rate": 1 }, "pointsFor": 21, "pointsAgainst": 0, "returns": 42, "misses": 0, "returnRate": { "n": 42, "count": 42, "rate": 1 } }, { "id": "kev-4b@150", "label": "Kev 4B", "kind": "model", "games": 7, "wins": 6, "draws": 0, "losses": 1, "scorePct": 85.7, "elo": 1070, "eloCI95": [ 1003, 1119 ], "moves": 506, "modelMoves": 506, "fallbackRate": { "n": 506, "count": 0, "rate": 0 }, "illegalRate": { "n": 506, "count": 0, "rate": 0 }, "errorRate": { "n": 506, "count": 0, "rate": 0 }, "latencyMs": { "n": 506, "mean": 509.4, "median": 476.9, "p95": 767.7 }, "latencyIsolatedMs": { "n": 47, "mean": 293.1, "median": 295.4, "p95": 305.8 }, "matchPerfect": { "n": 217, "count": 213, "rate": 0.9816 }, "matchPerfectOnDecisive": { "n": 217, "count": 213, "rate": 0.9816 }, "pointsFor": 18, "pointsAgainst": 6, "returns": 49, "misses": 6, "returnRate": { "n": 55, "count": 49, "rate": 0.8909 } }, { "id": "jev@150", "label": "Jev 1.13", "kind": "model", "games": 7, "wins": 5, "draws": 0, "losses": 2, "scorePct": 71.4, "elo": 1042, "eloCI95": [ 978, 1109 ], "moves": 443, "modelMoves": 443, "fallbackRate": { "n": 443, "count": 0, "rate": 0 }, "illegalRate": { "n": 443, "count": 0, "rate": 0 }, "errorRate": { "n": 443, "count": 0, "rate": 0 }, "latencyMs": { "n": 443, "mean": 156.8, "median": 149.7, "p95": 217.6 }, "latencyIsolatedMs": { "n": 1, "mean": 116.3, "median": 116.3, "p95": 116.3 }, "matchPerfect": { "n": 188, "count": 188, "rate": 1 }, "matchPerfectOnDecisive": { "n": 188, "count": 188, "rate": 1 }, "pointsFor": 15, "pointsAgainst": 8, "returns": 37, "misses": 8, "returnRate": { "n": 45, "count": 37, "rate": 0.8222 } }, { "id": "lev@150", "label": "lev 4B", "kind": "model", "games": 7, "wins": 4, "draws": 0, "losses": 3, "scorePct": 57.1, "elo": 1014, "eloCI95": [ 942, 1071 ], "moves": 469, "modelMoves": 469, "fallbackRate": { "n": 469, "count": 0, "rate": 0 }, "illegalRate": { "n": 469, "count": 0, "rate": 0 }, "errorRate": { "n": 469, "count": 0, "rate": 0 }, "latencyMs": { "n": 469, "mean": 939.6, "median": 932.9, "p95": 1319.9 }, "latencyIsolatedMs": { "n": 107, "mean": 512.8, "median": 439.9, "p95": 676.8 }, "matchPerfect": { "n": 191, "count": 188, "rate": 0.9843 }, "matchPerfectOnDecisive": { "n": 191, "count": 188, "rate": 0.9843 }, "pointsFor": 15, "pointsAgainst": 9, "returns": 40, "misses": 9, "returnRate": { "n": 49, "count": 40, "rate": 0.8163 } }, { "id": "clef-flash@150", "label": "Clef-Flash 9B", "kind": "model", "games": 7, "wins": 3, "draws": 0, "losses": 4, "scorePct": 42.9, "elo": 986, "eloCI95": [ 921, 1044 ], "moves": 505, "modelMoves": 505, "fallbackRate": { "n": 505, "count": 0, "rate": 0 }, "illegalRate": { "n": 505, "count": 0, "rate": 0 }, "errorRate": { "n": 505, "count": 0, "rate": 0 }, "latencyMs": { "n": 505, "mean": 754.8, "median": 762.6, "p95": 1067.2 }, "latencyIsolatedMs": { "n": 209, "mean": 630.8, "median": 554.3, "p95": 790.5 }, "matchPerfect": { "n": 228, "count": 178, "rate": 0.7807 }, "matchPerfectOnDecisive": { "n": 228, "count": 178, "rate": 0.7807 }, "pointsFor": 10, "pointsAgainst": 16, "returns": 39, "misses": 16, "returnRate": { "n": 55, "count": 39, "rate": 0.7091 } }, { "id": "julia-1@150", "label": "Julia-1", "kind": "model", "games": 7, "wins": 2, "draws": 0, "losses": 5, "scorePct": 28.6, "elo": 958, "eloCI95": [ 894, 1020 ], "moves": 243, "modelMoves": 243, "fallbackRate": { "n": 243, "count": 0, "rate": 0 }, "illegalRate": { "n": 243, "count": 0, "rate": 0 }, "errorRate": { "n": 243, "count": 0, "rate": 0 }, "latencyMs": { "n": 243, "mean": 75.7, "median": 65.8, "p95": 131.5 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 100, "count": 29, "rate": 0.29 }, "matchPerfectOnDecisive": { "n": 100, "count": 29, "rate": 0.29 }, "pointsFor": 8, "pointsAgainst": 17, "returns": 8, "misses": 17, "returnRate": { "n": 25, "count": 8, "rate": 0.32 } }, { "id": "random", "label": "random", "kind": "random", "games": 7, "wins": 1, "draws": 0, "losses": 6, "scorePct": 14.3, "elo": 930, "eloCI95": [ 883, 996 ], "moves": 222, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 92, "count": 23, "rate": 0.25 }, "matchPerfectOnDecisive": { "n": 92, "count": 23, "rate": 0.25 }, "pointsFor": 6, "pointsAgainst": 20, "returns": 9, "misses": 20, "returnRate": { "n": 29, "count": 9, "rate": 0.3103 } }, { "id": "laya@150", "label": "Laya", "kind": "model", "games": 7, "wins": 0, "draws": 0, "losses": 7, "scorePct": 0, "elo": 902, "eloCI95": [ 857, 966 ], "moves": 215, "modelMoves": 215, "fallbackRate": { "n": 215, "count": 0, "rate": 0 }, "illegalRate": { "n": 215, "count": 0, "rate": 0 }, "errorRate": { "n": 215, "count": 0, "rate": 0 }, "latencyMs": { "n": 215, "mean": 180.1, "median": 181.7, "p95": 265.8 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 97, "count": 13, "rate": 0.134 }, "matchPerfectOnDecisive": { "n": 97, "count": 13, "rate": 0.134 }, "pointsFor": 4, "pointsAgainst": 21, "returns": 3, "misses": 21, "returnRate": { "n": 24, "count": 3, "rate": 0.125 } } ], "h2h": [ { "a": "clef-flash@150", "b": "jev@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "clef-flash@150", "b": "julia-1@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "kev-4b@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "clef-flash@150", "b": "laya@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "lev@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "clef-flash@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "clef-flash@150", "b": "random", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "julia-1@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "kev-4b@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "jev@150", "b": "laya@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "lev@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "jev@150", "b": "random", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "kev-4b@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "julia-1@150", "b": "laya@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "lev@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "julia-1@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "julia-1@150", "b": "random", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "kev-4b@150", "b": "laya@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "kev-4b@150", "b": "lev@150", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "kev-4b@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "kev-4b@150", "b": "random", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "laya@150", "b": "lev@150", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "laya@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "laya@150", "b": "random", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "lev@150", "b": "perfect", "games": 1, "aWins": 0, "bWins": 1, "draws": 0 }, { "a": "lev@150", "b": "random", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 }, { "a": "perfect", "b": "random", "games": 1, "aWins": 1, "bWins": 0, "draws": 0 } ] } } }, { "id": "snake-fair", "files": [ "snake-fair-s1.jsonl" ], "matches": 72, "engine": "matches/1", "settings": { "elo": { "k": 32, "shuffles": 200, "bootstrapResamples": 200, "seed": 1, "start": 1000, "note": "mean of sequential Elo over seeded shuffles of all games; 95% interval from bootstrap over games" } }, "games": { "snake": { "matches": 72, "players": [ { "id": "expert", "label": "expert", "kind": "expert", "games": 16, "wins": 16, "draws": 0, "losses": 0, "scorePct": 100, "elo": 1185, "eloCI95": [ 1131, 1233 ], "moves": 441, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 441, "count": 441, "rate": 1 }, "matchPerfectOnDecisive": { "n": 438, "count": 438, "rate": 1 }, "expertApproved": { "n": 441, "count": 441, "rate": 1 }, "crashes": {}, "survivedGames": 16, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 27.6, "median": 16 }, "foodEaten": { "total": 52, "perGame": 3.25 } }, { "id": "jev@150", "label": "Jev 1.13", "kind": "model", "games": 16, "wins": 12, "draws": 1, "losses": 3, "scorePct": 78.1, "elo": 1103, "eloCI95": [ 1029, 1159 ], "moves": 1462, "modelMoves": 1462, "fallbackRate": { "n": 1462, "count": 0, "rate": 0 }, "illegalRate": { "n": 1462, "count": 0, "rate": 0 }, "errorRate": { "n": 1462, "count": 0, "rate": 0 }, "latencyMs": { "n": 1462, "mean": 142.8, "median": 134.6, "p95": 193.3 }, "latencyIsolatedMs": { "n": 1, "mean": 132.6, "median": 132.6, "p95": 132.6 }, "matchPerfect": { "n": 1462, "count": 1452, "rate": 0.9932 }, "matchPerfectOnDecisive": { "n": 1460, "count": 1450, "rate": 0.9932 }, "expertApproved": { "n": 1462, "count": 1452, "rate": 0.9932 }, "crashes": { "wall": 2, "head_on": 1 }, "survivedGames": 13, "timeoutGames": 2, "survivalTicks": { "n": 16, "mean": 91.4, "median": 19 }, "foodEaten": { "total": 8, "perGame": 0.5 } }, { "id": "clef@150", "label": "Clef 27B", "kind": "model", "games": 16, "wins": 11, "draws": 0, "losses": 5, "scorePct": 68.8, "elo": 1068, "eloCI95": [ 997, 1150 ], "moves": 519, "modelMoves": 519, "fallbackRate": { "n": 519, "count": 0, "rate": 0 }, "illegalRate": { "n": 519, "count": 0, "rate": 0 }, "errorRate": { "n": 519, "count": 0, "rate": 0 }, "latencyMs": { "n": 519, "mean": 4400.8, "median": 4295.5, "p95": 5632.7 }, "latencyIsolatedMs": { "n": 3, "mean": 3054.5, "median": 2687.9, "p95": 3790.2 }, "matchPerfect": { "n": 519, "count": 318, "rate": 0.6127 }, "matchPerfectOnDecisive": { "n": 508, "count": 307, "rate": 0.6043 }, "expertApproved": { "n": 519, "count": 318, "rate": 0.6127 }, "crashes": { "wall": 3, "body_opponent": 1 }, "survivedGames": 12, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 32.4, "median": 18 }, "foodEaten": { "total": 15, "perGame": 0.94 } }, { "id": "clef-flash@150", "label": "Clef-Flash 9B", "kind": "model", "games": 16, "wins": 9, "draws": 1, "losses": 6, "scorePct": 59.4, "elo": 1034, "eloCI95": [ 946, 1110 ], "moves": 1070, "modelMoves": 1070, "fallbackRate": { "n": 1070, "count": 0, "rate": 0 }, "illegalRate": { "n": 1070, "count": 0, "rate": 0 }, "errorRate": { "n": 1070, "count": 0, "rate": 0 }, "latencyMs": { "n": 1070, "mean": 1726.4, "median": 1681.4, "p95": 2076.9 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 1070, "count": 181, "rate": 0.1692 }, "matchPerfectOnDecisive": { "n": 1069, "count": 180, "rate": 0.1684 }, "expertApproved": { "n": 1070, "count": 181, "rate": 0.1692 }, "crashes": { "wall": 3, "body_opponent": 1 }, "survivedGames": 12, "timeoutGames": 2, "survivalTicks": { "n": 16, "mean": 66.9, "median": 15 }, "foodEaten": { "total": 5, "perGame": 0.31 } }, { "id": "julia-1@150", "label": "Julia-1", "kind": "model", "games": 16, "wins": 9, "draws": 0, "losses": 7, "scorePct": 56.3, "elo": 1022, "eloCI95": [ 949, 1104 ], "moves": 913, "modelMoves": 913, "fallbackRate": { "n": 913, "count": 0, "rate": 0 }, "illegalRate": { "n": 913, "count": 0, "rate": 0 }, "errorRate": { "n": 913, "count": 0, "rate": 0 }, "latencyMs": { "n": 913, "mean": 230.3, "median": 241.6, "p95": 317.5 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 913, "count": 108, "rate": 0.1183 }, "matchPerfectOnDecisive": { "n": 912, "count": 107, "rate": 0.1173 }, "expertApproved": { "n": 913, "count": 108, "rate": 0.1183 }, "crashes": { "wall": 6 }, "survivedGames": 10, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 57.1, "median": 22.5 }, "foodEaten": { "total": 1, "perGame": 0.06 } }, { "id": "random", "label": "random", "kind": "random", "games": 16, "wins": 6, "draws": 0, "losses": 10, "scorePct": 37.5, "elo": 954, "eloCI95": [ 878, 1049 ], "moves": 275, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 275, "count": 135, "rate": 0.4909 }, "matchPerfectOnDecisive": { "n": 273, "count": 133, "rate": 0.4872 }, "expertApproved": { "n": 275, "count": 135, "rate": 0.4909 }, "crashes": { "wall": 8, "head_on": 1, "body_opponent": 1 }, "survivedGames": 6, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 17.2, "median": 16 }, "foodEaten": { "total": 5, "perGame": 0.31 } }, { "id": "lev@150", "label": "lev 4B", "kind": "model", "games": 16, "wins": 4, "draws": 0, "losses": 12, "scorePct": 25, "elo": 908, "eloCI95": [ 838, 984 ], "moves": 202, "modelMoves": 202, "fallbackRate": { "n": 202, "count": 0, "rate": 0 }, "illegalRate": { "n": 202, "count": 0, "rate": 0 }, "errorRate": { "n": 202, "count": 0, "rate": 0 }, "latencyMs": { "n": 202, "mean": 2076.7, "median": 2111.9, "p95": 2629.7 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 202, "count": 118, "rate": 0.5842 }, "matchPerfectOnDecisive": { "n": 198, "count": 114, "rate": 0.5758 }, "expertApproved": { "n": 202, "count": 118, "rate": 0.5842 }, "crashes": { "wall": 11, "body_opponent": 1 }, "survivedGames": 4, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 12.6, "median": 12.5 }, "foodEaten": { "total": 4, "perGame": 0.25 } }, { "id": "kev-4b@150", "label": "Kev 4B", "kind": "model", "games": 16, "wins": 2, "draws": 1, "losses": 13, "scorePct": 15.6, "elo": 875, "eloCI95": [ 818, 949 ], "moves": 212, "modelMoves": 212, "fallbackRate": { "n": 212, "count": 0, "rate": 0 }, "illegalRate": { "n": 212, "count": 0, "rate": 0 }, "errorRate": { "n": 212, "count": 0, "rate": 0 }, "latencyMs": { "n": 212, "mean": 1422.5, "median": 1450.4, "p95": 1801.8 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 212, "count": 131, "rate": 0.6179 }, "matchPerfectOnDecisive": { "n": 209, "count": 128, "rate": 0.6124 }, "expertApproved": { "n": 212, "count": 131, "rate": 0.6179 }, "crashes": { "wall": 13, "body_opponent": 1 }, "survivedGames": 2, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 13.3, "median": 12.5 }, "foodEaten": { "total": 7, "perGame": 0.44 } }, { "id": "laya@150", "label": "Laya", "kind": "model", "games": 16, "wins": 1, "draws": 1, "losses": 14, "scorePct": 9.4, "elo": 850, "eloCI95": [ 794, 932 ], "moves": 226, "modelMoves": 226, "fallbackRate": { "n": 226, "count": 0, "rate": 0 }, "illegalRate": { "n": 226, "count": 0, "rate": 0 }, "errorRate": { "n": 226, "count": 0, "rate": 0 }, "latencyMs": { "n": 226, "mean": 434.9, "median": 454.2, "p95": 569.2 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 226, "count": 102, "rate": 0.4513 }, "matchPerfectOnDecisive": { "n": 223, "count": 99, "rate": 0.4439 }, "expertApproved": { "n": 226, "count": 102, "rate": 0.4513 }, "crashes": { "wall": 12, "body_opponent": 2, "head_on": 1 }, "survivedGames": 1, "timeoutGames": 0, "survivalTicks": { "n": 16, "mean": 14.1, "median": 15 }, "foodEaten": { "total": 2, "perGame": 0.13 } } ], "h2h": [ { "a": "clef-flash@150", "b": "clef@150", "games": 2, "aWins": 0, "bWins": 2, "draws": 0 }, { "a": "clef-flash@150", "b": "expert", "games": 2, "aWins": 0, "bWins": 2, "draws": 0 }, { "a": "clef-flash@150", "b": "jev@150", "games": 2, "aWins": 0, "bWins": 1, "draws": 1 }, { "a": "clef-flash@150", "b": "julia-1@150", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "clef-flash@150", "b": "kev-4b@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "laya@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "lev@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "random", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "clef@150", "b": "expert", "games": 2, "aWins": 0, "bWins": 2, "draws": 0 }, { "a": "clef@150", "b": "jev@150", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "clef@150", "b": "julia-1@150", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "clef@150", "b": "kev-4b@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "clef@150", "b": "laya@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "clef@150", "b": "lev@150", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "clef@150", "b": "random", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "jev@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "julia-1@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "kev-4b@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "laya@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "lev@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "random", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "julia-1@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "kev-4b@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "laya@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "lev@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "random", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "kev-4b@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "laya@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "lev@150", "games": 2, "aWins": 2, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "random", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "kev-4b@150", "b": "laya@150", "games": 2, "aWins": 1, "bWins": 0, "draws": 1 }, { "a": "kev-4b@150", "b": "lev@150", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "kev-4b@150", "b": "random", "games": 2, "aWins": 0, "bWins": 2, "draws": 0 }, { "a": "laya@150", "b": "lev@150", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 }, { "a": "laya@150", "b": "random", "games": 2, "aWins": 0, "bWins": 2, "draws": 0 }, { "a": "lev@150", "b": "random", "games": 2, "aWins": 1, "bWins": 1, "draws": 0 } ] } } }, { "id": "tron-fair", "files": [ "tron-fair-s1.jsonl" ], "matches": 144, "engine": "matches/1", "settings": { "elo": { "k": 32, "shuffles": 200, "bootstrapResamples": 200, "seed": 1, "start": 1000, "note": "mean of sequential Elo over seeded shuffles of all games; 95% interval from bootstrap over games" } }, "games": { "tron": { "matches": 144, "players": [ { "id": "expert", "label": "expert", "kind": "expert", "games": 32, "wins": 30, "draws": 2, "losses": 0, "scorePct": 96.9, "elo": 1267, "eloCI95": [ 1206, 1311 ], "moves": 644, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 644, "count": 644, "rate": 1 }, "matchPerfectOnDecisive": { "n": 631, "count": 631, "rate": 1 }, "expertApproved": { "n": 644, "count": 644, "rate": 1 }, "crashes": { "head_on": 2 }, "survivedGames": 30, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 20.1, "median": 17.5 } }, { "id": "jev@150", "label": "Jev 1.13", "kind": "model", "games": 32, "wins": 27, "draws": 3, "losses": 2, "scorePct": 89.1, "elo": 1219, "eloCI95": [ 1170, 1280 ], "moves": 678, "modelMoves": 678, "fallbackRate": { "n": 678, "count": 0, "rate": 0 }, "illegalRate": { "n": 678, "count": 0, "rate": 0 }, "errorRate": { "n": 678, "count": 0, "rate": 0 }, "latencyMs": { "n": 678, "mean": 139.9, "median": 135.3, "p95": 177.2 }, "latencyIsolatedMs": { "n": 1, "mean": 126.6, "median": 126.6, "p95": 126.6 }, "matchPerfect": { "n": 678, "count": 447, "rate": 0.6593 }, "matchPerfectOnDecisive": { "n": 653, "count": 422, "rate": 0.6462 }, "expertApproved": { "n": 678, "count": 447, "rate": 0.6593 }, "crashes": { "trail_own": 1, "trail_opponent": 1, "head_on": 3 }, "survivedGames": 27, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 21.2, "median": 17.5 } }, { "id": "kev-4b@150", "label": "Kev 4B", "kind": "model", "games": 32, "wins": 17, "draws": 2, "losses": 13, "scorePct": 56.3, "elo": 1031, "eloCI95": [ 959, 1126 ], "moves": 536, "modelMoves": 536, "fallbackRate": { "n": 536, "count": 0, "rate": 0 }, "illegalRate": { "n": 536, "count": 0, "rate": 0 }, "errorRate": { "n": 536, "count": 0, "rate": 0 }, "latencyMs": { "n": 536, "mean": 887.4, "median": 896.7, "p95": 1331.9 }, "latencyIsolatedMs": { "n": 1, "mean": 365.1, "median": 365.1, "p95": 365.1 }, "matchPerfect": { "n": 536, "count": 307, "rate": 0.5728 }, "matchPerfectOnDecisive": { "n": 523, "count": 294, "rate": 0.5621 }, "expertApproved": { "n": 536, "count": 307, "rate": 0.5728 }, "crashes": { "wall": 11, "trail_opponent": 2, "head_on": 2 }, "survivedGames": 17, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 16.8, "median": 17 } }, { "id": "clef-flash@150", "label": "Clef-Flash 9B", "kind": "model", "games": 32, "wins": 17, "draws": 1, "losses": 14, "scorePct": 54.7, "elo": 1025, "eloCI95": [ 938, 1083 ], "moves": 542, "modelMoves": 542, "fallbackRate": { "n": 542, "count": 0, "rate": 0 }, "illegalRate": { "n": 542, "count": 0, "rate": 0 }, "errorRate": { "n": 542, "count": 0, "rate": 0 }, "latencyMs": { "n": 542, "mean": 1313.4, "median": 1309.2, "p95": 1926.4 }, "latencyIsolatedMs": { "n": 47, "mean": 688.6, "median": 597.3, "p95": 893.4 }, "matchPerfect": { "n": 542, "count": 289, "rate": 0.5332 }, "matchPerfectOnDecisive": { "n": 535, "count": 282, "rate": 0.5271 }, "expertApproved": { "n": 542, "count": 289, "rate": 0.5332 }, "crashes": { "trail_own": 8, "trail_opponent": 5, "head_on": 1, "wall": 1 }, "survivedGames": 17, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 16.9, "median": 16.5 } }, { "id": "lev@150", "label": "lev 4B", "kind": "model", "games": 32, "wins": 14, "draws": 3, "losses": 15, "scorePct": 48.4, "elo": 991, "eloCI95": [ 930, 1075 ], "moves": 444, "modelMoves": 444, "fallbackRate": { "n": 444, "count": 0, "rate": 0 }, "illegalRate": { "n": 444, "count": 0, "rate": 0 }, "errorRate": { "n": 444, "count": 0, "rate": 0 }, "latencyMs": { "n": 444, "mean": 1404.2, "median": 1398.9, "p95": 2220 }, "latencyIsolatedMs": { "n": 45, "mean": 542.3, "median": 463.8, "p95": 837 }, "matchPerfect": { "n": 444, "count": 175, "rate": 0.3941 }, "matchPerfectOnDecisive": { "n": 444, "count": 175, "rate": 0.3941 }, "expertApproved": { "n": 444, "count": 175, "rate": 0.3941 }, "crashes": { "trail_own": 2, "trail_opponent": 3, "wall": 12, "head_on": 1 }, "survivedGames": 14, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 13.9, "median": 13 } }, { "id": "clef@150", "label": "Clef 27B", "kind": "model", "games": 32, "wins": 12, "draws": 3, "losses": 17, "scorePct": 42.2, "elo": 956, "eloCI95": [ 885, 1024 ], "moves": 417, "modelMoves": 417, "fallbackRate": { "n": 417, "count": 0, "rate": 0 }, "illegalRate": { "n": 417, "count": 0, "rate": 0 }, "errorRate": { "n": 417, "count": 0, "rate": 0 }, "latencyMs": { "n": 417, "mean": 2910.2, "median": 2518.6, "p95": 5175.2 }, "latencyIsolatedMs": { "n": 249, "mean": 2262.4, "median": 2311.6, "p95": 2575.4 }, "matchPerfect": { "n": 417, "count": 232, "rate": 0.5564 }, "matchPerfectOnDecisive": { "n": 412, "count": 227, "rate": 0.551 }, "expertApproved": { "n": 417, "count": 232, "rate": 0.5564 }, "crashes": { "trail_own": 14, "trail_opponent": 5, "head_on": 1 }, "survivedGames": 12, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 13, "median": 12 } }, { "id": "random", "label": "random", "kind": "random", "games": 32, "wins": 8, "draws": 4, "losses": 20, "scorePct": 31.3, "elo": 898, "eloCI95": [ 828, 963 ], "moves": 343, "modelMoves": 0, "fallbackRate": { "n": 0, "count": 0, "rate": null }, "illegalRate": { "n": 0, "count": 0, "rate": null }, "errorRate": { "n": 0, "count": 0, "rate": null }, "latencyMs": { "n": 0, "mean": null, "median": null, "p95": null }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 343, "count": 124, "rate": 0.3615 }, "matchPerfectOnDecisive": { "n": 343, "count": 124, "rate": 0.3615 }, "expertApproved": { "n": 343, "count": 124, "rate": 0.3615 }, "crashes": { "wall": 4, "trail_opponent": 2, "trail_own": 15, "head_on": 3 }, "survivedGames": 8, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 10.7, "median": 10 } }, { "id": "laya@150", "label": "Laya", "kind": "model", "games": 32, "wins": 7, "draws": 1, "losses": 24, "scorePct": 23.4, "elo": 852, "eloCI95": [ 769, 937 ], "moves": 277, "modelMoves": 277, "fallbackRate": { "n": 277, "count": 0, "rate": 0 }, "illegalRate": { "n": 277, "count": 0, "rate": 0 }, "errorRate": { "n": 277, "count": 0, "rate": 0 }, "latencyMs": { "n": 277, "mean": 275.9, "median": 270.2, "p95": 454.5 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 277, "count": 5, "rate": 0.0181 }, "matchPerfectOnDecisive": { "n": 276, "count": 4, "rate": 0.0145 }, "expertApproved": { "n": 277, "count": 5, "rate": 0.0181 }, "crashes": { "wall": 25 }, "survivedGames": 7, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 8.7, "median": 8.5 } }, { "id": "julia-1@150", "label": "Julia-1", "kind": "model", "games": 32, "wins": 2, "draws": 1, "losses": 29, "scorePct": 7.8, "elo": 761, "eloCI95": [ 706, 821 ], "moves": 197, "modelMoves": 197, "fallbackRate": { "n": 197, "count": 0, "rate": 0 }, "illegalRate": { "n": 197, "count": 0, "rate": 0 }, "errorRate": { "n": 197, "count": 0, "rate": 0 }, "latencyMs": { "n": 197, "mean": 143.3, "median": 128.6, "p95": 259.8 }, "latencyIsolatedMs": { "n": 0, "mean": null, "median": null, "p95": null }, "matchPerfect": { "n": 197, "count": 39, "rate": 0.198 }, "matchPerfectOnDecisive": { "n": 189, "count": 31, "rate": 0.164 }, "expertApproved": { "n": 197, "count": 39, "rate": 0.198 }, "crashes": { "trail_own": 29, "head_on": 1 }, "survivedGames": 2, "timeoutGames": 0, "survivalTicks": { "n": 32, "mean": 6.2, "median": 5.5 } } ], "h2h": [ { "a": "clef-flash@150", "b": "clef@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "expert", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef-flash@150", "b": "jev@150", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef-flash@150", "b": "julia-1@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "clef-flash@150", "b": "kev-4b@150", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "clef-flash@150", "b": "laya@150", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "clef-flash@150", "b": "lev@150", "games": 4, "aWins": 2, "bWins": 2, "draws": 0 }, { "a": "clef-flash@150", "b": "random", "games": 4, "aWins": 2, "bWins": 1, "draws": 1 }, { "a": "clef@150", "b": "expert", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef@150", "b": "jev@150", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "clef@150", "b": "julia-1@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "clef@150", "b": "kev-4b@150", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "clef@150", "b": "laya@150", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "clef@150", "b": "lev@150", "games": 4, "aWins": 2, "bWins": 0, "draws": 2 }, { "a": "clef@150", "b": "random", "games": 4, "aWins": 2, "bWins": 1, "draws": 1 }, { "a": "expert", "b": "jev@150", "games": 4, "aWins": 2, "bWins": 0, "draws": 2 }, { "a": "expert", "b": "julia-1@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "kev-4b@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "laya@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "lev@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "expert", "b": "random", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "julia-1@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "kev-4b@150", "games": 4, "aWins": 3, "bWins": 0, "draws": 1 }, { "a": "jev@150", "b": "laya@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "lev@150", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "jev@150", "b": "random", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 }, { "a": "julia-1@150", "b": "kev-4b@150", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "julia-1@150", "b": "laya@150", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "julia-1@150", "b": "lev@150", "games": 4, "aWins": 0, "bWins": 3, "draws": 1 }, { "a": "julia-1@150", "b": "random", "games": 4, "aWins": 1, "bWins": 3, "draws": 0 }, { "a": "kev-4b@150", "b": "laya@150", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "kev-4b@150", "b": "lev@150", "games": 4, "aWins": 3, "bWins": 1, "draws": 0 }, { "a": "kev-4b@150", "b": "random", "games": 4, "aWins": 3, "bWins": 0, "draws": 1 }, { "a": "laya@150", "b": "lev@150", "games": 4, "aWins": 0, "bWins": 4, "draws": 0 }, { "a": "laya@150", "b": "random", "games": 4, "aWins": 0, "bWins": 3, "draws": 1 }, { "a": "lev@150", "b": "random", "games": 4, "aWins": 4, "bWins": 0, "draws": 0 } ] } } } ] }