pluto-2.1 / benchmarks /pluto21_typed_test.json
henryphilf's picture
Expand public evaluation set and regenerate frontier charts
4649798 verified
Raw History Blame Contribute Delete
912 Bytes
{
"model": "pluto-2.1-1.7b-step2000",
"benchmark": "LocalLLaMA/typed-decisions",
"split": "test",
"mode": "fitted",
"n": 2000,
"accuracy": 0.6695,
"kl": 0.21389316512223397,
"brier": 0.12613537464071567,
"ece": 0.05558588827160893,
"by_kind": {
"choice": {
"n": 600,
"accuracy": 0.725,
"kl": 0.2037330221309278,
"brier": 0.10235709260413375,
"ece": 0.10109364924647721
},
"noul": {
"n": 600,
"accuracy": 0.735,
"kl": 0.15611870023697572,
"brier": 0.12411358328130827,
"ece": 0.05807213359097196
},
"score": {
"n": 800,
"accuracy": 0.57875,
"kl": 0.26484412102965726,
"brier": 0.14548542968770764,
"ece": 0.036768776402162195
}
},
"latency_ms_single_p50": 86.26855001784861,
"params_b": 1.738,
"lineage": "Qwen3-1.7B -> Bosun 3.1 1.7B -> Pluto-2.1 2000-step fine-tune"
}