48 lines
1.5 KiB
JSON
48 lines
1.5 KiB
JSON
{
|
|
"id": "49d4a8c7-df2d-41cb-9010-53f91ff42b93",
|
|
"started_at": "2026-09-26T22:56:39.933045",
|
|
"updated_at": "2026-09-26T23:10:13.434208",
|
|
"finished_at": "2026-09-26T23:10:13.434208",
|
|
"n_total_trials": 4,
|
|
"stats": {
|
|
"n_completed_trials": 4,
|
|
"n_errored_trials": 0,
|
|
"n_running_trials": 0,
|
|
"n_pending_trials": 0,
|
|
"n_cancelled_trials": 0,
|
|
"n_retries": 0,
|
|
"evals": {
|
|
"codex__gpt-5.6-sol__adhoc": {
|
|
"n_trials": 4,
|
|
"n_errors": 0,
|
|
"metrics": [
|
|
{
|
|
"mean": 0.4675
|
|
}
|
|
],
|
|
"pass_at_k": {},
|
|
"reward_stats": {
|
|
"reward": {
|
|
"0.52": [
|
|
"mishandled_pro_v2__DjvdVkm"
|
|
],
|
|
"0.41": [
|
|
"mishandled_pro_v2__p7644rd"
|
|
],
|
|
"0.51": [
|
|
"mishandled_pro_v2__2JvrM24"
|
|
],
|
|
"0.43": [
|
|
"mishandled_pro_v2__a5pdbqx"
|
|
]
|
|
}
|
|
},
|
|
"exception_stats": {}
|
|
}
|
|
},
|
|
"n_input_tokens": 16043202,
|
|
"n_cache_tokens": 15528667,
|
|
"n_output_tokens": 99253,
|
|
"cost_usd": 10.2546668
|
|
}
|
|
} |