48 lines
1.5 KiB
JSON
48 lines
1.5 KiB
JSON
{
|
|
"id": "43bf5859-3031-4d52-8f1a-7abeca6a7cf1",
|
|
"started_at": "2026-09-22T00:18:30.307753",
|
|
"updated_at": "2026-09-22T00:34:46.521147",
|
|
"finished_at": "2026-09-22T00:34:46.521147",
|
|
"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": 0.5125
|
|
}
|
|
],
|
|
"pass_at_k": {},
|
|
"reward_stats": {
|
|
"reward": {
|
|
"0.42": [
|
|
"mishandle_pro_v2__WEApqta"
|
|
],
|
|
"0.63": [
|
|
"mishandle_pro_v2__44bVYzE"
|
|
],
|
|
"0.53": [
|
|
"mishandle_pro_v2__8fFS8Dk"
|
|
],
|
|
"0.47": [
|
|
"mishandle_pro_v2__Ed9uesZ"
|
|
]
|
|
}
|
|
},
|
|
"exception_stats": {}
|
|
}
|
|
},
|
|
"n_input_tokens": 12052446,
|
|
"n_cache_tokens": 11597094,
|
|
"n_output_tokens": 97154,
|
|
"cost_usd": 8.403325599999999
|
|
}
|
|
} |