pluto-2.1 / benchmarks /pluto21_decisionbench_390.json
henryphilf's picture
Expand public evaluation set and regenerate frontier charts
4649798 verified
Raw History Blame Contribute Delete
938 Bytes
{
"model": "pluto-2.1-1.7b-step2000",
"benchmark": "Hanno-Labs/decision-bench",
"split": "eval",
"rows": 390,
"n": 390,
"accuracy": 0.7307692307692307,
"nll": 0.782475716850374,
"brier": 0.38374544733999405,
"ece": 0.07872579764729119,
"by_primitive": {
"ordinal_scoring": {
"n": 36,
"accuracy": 0.3055555555555556,
"nll": 1.5345522148320503,
"brier": 0.6649819753906753,
"ece": 0.14113543406196793
},
"candidate_selection": {
"n": 222,
"accuracy": 0.7297297297297297,
"nll": 0.8837282527930221,
"brier": 0.41591003706917623,
"ece": 0.0940529449476535
},
"binary_classification": {
"n": 132,
"accuracy": 0.8484848484848485,
"nll": 0.4070755887700082,
"brier": 0.2529495842361836,
"ece": 0.10125961085499781
}
},
"latency_s": 47.35091979999561,
"params_b": 1.738
}