loudink-v1.1 / product_scorecard.json
nsalerni's picture
loudink-v1.1 1.1.0: skills PR-A–E canary (record/replay, slots, expanded daily-mac)
d506628 verified
Raw
History Blame
2.5 kB
{
"reports": [
{
"source": "artifacts/benchmarks/loudink_v1/daily_mac/loudink_v1_daily_mac_measurement.json",
"label": "loudink-v1 v0.4 daily-mac product",
"writing": {
"shipped": {
"total": 25,
"passed": 25,
"accuracy": 1.0
},
"neural": {
"total": 25,
"passed": 23,
"accuracy": 0.92,
"missing": 0
},
"polish_lift": 0.07999999999999996,
"latency": {
"n": 25,
"mean": 166.6401715839654,
"p50": 171.05649993754923,
"p95": 332.83937512896955,
"max": 383.80437484011054,
"model_invoked_p50": 176.41600011847913,
"model_invoked_p95": 332.83937512896955,
"model_invoked_n": 20,
"fast_path_rate": 0.19999999999999996
}
},
"computer": {
"shipped": {
"total": 44,
"passed": 44,
"accuracy": 1.0
},
"neural": {
"total": 44,
"passed": 0,
"accuracy": 0.0,
"missing": 44
},
"latency": {
"n": 44,
"mean": 0.05,
"p50": 0.05,
"p95": 0.05,
"max": 0.05,
"model_invoked_p50": 0.0,
"model_invoked_p95": 0.0,
"model_invoked_n": 0,
"fast_path_rate": 1.0
}
},
"multi_step": {
"shipped": {
"total": 25,
"passed": 25,
"accuracy": 1.0
},
"latency": {
"n": 25,
"mean": 0.05,
"p50": 0.05,
"p95": 0.05,
"max": 0.05,
"model_invoked_p50": 0.0,
"model_invoked_p95": 0.0,
"model_invoked_n": 0,
"fast_path_rate": 1.0
},
"n": 25
},
"overall": {
"shipped": {
"total": 69,
"passed": 69,
"accuracy": 1.0
},
"latency": {
"n": 69,
"mean": 60.40875782027732,
"p50": 0.05,
"p95": 323.94058303907514,
"max": 383.80437484011054,
"model_invoked_p50": 176.41600011847913,
"model_invoked_p95": 332.83937512896955,
"model_invoked_n": 20,
"fast_path_rate": 0.7101449275362319
}
},
"finish_reasons": {
"transcript_ir_fast_path": 44,
"loudink_v1_structural_polish": 20,
"transcript_polish_fast_path": 5
}
}
]
}