pluto-2.1 / benchmarks /pluto2_decisionbench_1565.json
henryphilf's picture
Expand public evaluation set and regenerate frontier charts
4649798 verified
Raw History Blame Contribute Delete
3.95 kB
{
"model": "C:\\Users\\henry\\new-omida-project\\pluto-2\\artifacts\\pluto-2",
"benchmark": "Hanno-Labs/decision-bench",
"split": "eval",
"requested_rows": 1992,
"included_rows": 1565,
"skipped_options": 403,
"skipped_prompt": 24,
"max_len": 2048,
"max_options": 16,
"batch_size": 8,
"n": 1565,
"accuracy": 0.5789137380191693,
"nll": 1.086787512493374,
"brier": 0.5476896818997071,
"ece": 0.03040878511978975,
"by_primitive": {
"ordinal_scoring": {
"n": 142,
"accuracy": 0.31690140845070425,
"nll": 1.702245548212995,
"brier": 0.7919354885271652,
"ece": 0.23922968191870858
},
"candidate_selection": {
"n": 893,
"accuracy": 0.5139977603583427,
"nll": 1.3175748448567437,
"brier": 0.6268954549540386,
"ece": 0.05335862384965334
},
"binary_classification": {
"n": 530,
"accuracy": 0.7584905660377359,
"nll": 0.5330363259411564,
"brier": 0.34879598401552414,
"ece": 0.06172943167517076
}
},
"by_candidate_count_bucket": {
"2": {
"n": 571,
"accuracy": 0.7758318739054291,
"nll": 0.5050864657848015,
"brier": 0.327164851226164,
"ece": 0.06657381248932939
},
"3": {
"n": 52,
"accuracy": 0.7307692307692307,
"nll": 0.8230841673369436,
"brier": 0.4656287957639696,
"ece": 0.1768807057572377
},
"4": {
"n": 417,
"accuracy": 0.38369304556354916,
"nll": 1.3917934761391375,
"brier": 0.7077339030970196,
"ece": 0.1366008560847453
},
"5": {
"n": 53,
"accuracy": 0.41509433962264153,
"nll": 1.3906180619397066,
"brier": 0.6965652674513569,
"ece": 0.12229648836302624
},
"6": {
"n": 62,
"accuracy": 0.5161290322580645,
"nll": 1.4950352941490053,
"brier": 0.7103141629730844,
"ece": 0.20879640991101237
},
"7": {
"n": 45,
"accuracy": 0.4444444444444444,
"nll": 1.6899349194297915,
"brier": 0.7423954014990986,
"ece": 0.12905421665120007
},
"8": {
"n": 84,
"accuracy": 0.7738095238095238,
"nll": 0.9060157136010754,
"brier": 0.3785204070880192,
"ece": 0.24301153029444017
},
"9": {
"n": 204,
"accuracy": 0.36764705882352944,
"nll": 1.8435587409953924,
"brier": 0.812923101907946,
"ece": 0.22095318662488653
},
"10": {
"n": 20,
"accuracy": 0.55,
"nll": 1.3466658370996674,
"brier": 0.581430754465156,
"ece": 0.19840851353183617
},
"11": {
"n": 11,
"accuracy": 0.45454545454545453,
"nll": 1.742375978409565,
"brier": 0.7057783122595841,
"ece": 0.14119367689162138
},
"12": {
"n": 5,
"accuracy": 0.6,
"nll": 1.60027353448161,
"brier": 0.7113295784136134,
"ece": 0.3569272335501148
},
"13": {
"n": 2,
"accuracy": 0.0,
"nll": 2.7291098611081326,
"brier": 1.0117958954704067,
"ece": 0.26010035168011614
},
"14": {
"n": 5,
"accuracy": 0.2,
"nll": 2.0200694744604966,
"brier": 0.8290373434160234,
"ece": 0.08302967212398918
},
"15": {
"n": 4,
"accuracy": 0.75,
"nll": 1.4792958719146407,
"brier": 0.6844986526248836,
"ece": 0.4951474916901011
},
"16": {
"n": 30,
"accuracy": 0.9333333333333333,
"nll": 0.6343312692816507,
"brier": 0.23775440952147306,
"ece": 0.2986224605056543
}
},
"prompt_state_truncated": 48,
"latency_s": 21.23680189999868,
"latency_ms_per_row": 13.56984146964772,
"length_tokens": {
"p50": 250,
"p90": 662,
"p95": 1086,
"p99": 2048,
"max": 2048
}
}