pluto-2.1 / benchmarks /pluto21_decisionbench_1565.json
henryphilf's picture
Expand public evaluation set and regenerate frontier charts
4649798 verified
Raw History Blame Contribute Delete
1.02 kB
{
"model": "pluto-2.1-1.7b-step2000",
"benchmark": "Hanno-Labs/decision-bench",
"split": "eval",
"rows": 1565,
"n": 1565,
"accuracy": 0.7207667731629392,
"nll": 0.743893769561289,
"brier": 0.37302688896067215,
"ece": 0.05858011190501126,
"by_primitive": {
"ordinal_scoring": {
"n": 142,
"accuracy": 0.29577464788732394,
"nll": 1.5536898785809998,
"brier": 0.699555331279626,
"ece": 0.155038637254273
},
"candidate_selection": {
"n": 893,
"accuracy": 0.7491601343784995,
"nll": 0.7901911483528816,
"brier": 0.3715472431253504,
"ece": 0.09278790573727526
},
"binary_classification": {
"n": 530,
"accuracy": 0.7867924528301887,
"nll": 0.44892281344489054,
"brier": 0.28803497371850384,
"ece": 0.04888898737294541
}
},
"latency_s": 191.43742590001784,
"params_b": 1.738,
"lineage": "Qwen3-1.7B -> Bosun 3.1 1.7B -> Pluto-2.1 2000-step fine-tune"
}