Run success rate

Run success rate

Tasks the run solved on its last attempt / tasks attempted in this run.

Formula: COUNT(distinct tasks where last attempt passed) / COUNT(distinct tasks attempted in this run)

Per-run metric for the model's "final answer" on each task. Differs from leaderboard pass_at_n: this denominator is the run's own attempted-task count, not the task set size, so partial runs are not penalised for unattempted tasks.

28.1% 18/64 of 64 tasks attempted in this run
Avg score

Avg attempt score

Mean per-attempt score on a 0–100 point scale (partial credit). Drill-down only.

Formula: Mean of attempt scores across all results rows: SUM(score) / COUNT(*) over the results table. Each attempt earns 0–100 points based on compile + test outcomes.

Drill-down companion to pass_at_n. Rewards partial credit but not directly comparable to pass rate; use for within-model analysis.

18.9 / 100
Cost $0.40
Duration 2h 24m
Filter:
Per-task results for run d484f310-e4bc-42e1-bc28-0ea7ba183a81
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK3m 2s
CG-AL-E002easy2100.0 / 1006/6OK3m 17s
CG-AL-E003easy1100.0 / 1005/5OK2m 50s
CG-AL-E004easy20.0 / 1000/0FAIL14.8s
CG-AL-E005easy20.0 / 1000/0FAIL2m 6s
CG-AL-E006easy1100.0 / 1007/7OK3m 30s
CG-AL-E007easy20.0 / 1000/0FAIL13.2s
CG-AL-E008easy20.0 / 1000/0FAIL11.1s
CG-AL-E009easy20.0 / 1000/0FAIL57.9s
CG-AL-E010easy20.0 / 1000/0FAIL14.1s
CG-AL-E031easy1100.0 / 1003/3OK3m 0s
CG-AL-E032easy20.0 / 1000/0FAIL10.7s
CG-AL-E045easy2100.0 / 1004/4OK3m 34s
CG-AL-E050easy20.0 / 1000/0FAIL11m 52s
CG-AL-E051easy1100.0 / 10015/15OK6m 3s
CG-AL-E052easy20.0 / 1000/0FAIL1m 37s
CG-AL-E053easy1100.0 / 1003/3OK2m 55s
CG-AL-E054easy20.0 / 1000/0FAIL36.4s
CG-AL-E055easy1100.0 / 1008/8OK2m 45s
CG-AL-H001hard1100.0 / 10025/25OK3m 26s
CG-AL-H002hard2100.0 / 1004/4OK2m 44s
CG-AL-H003hard262.5 / 1003/5OK3m 41s
CG-AL-H004hard1100.0 / 10014/14OK3m 15s
CG-AL-H005hard262.5 / 1002/5OK3m 10s
CG-AL-H006hard20.0 / 1000/0FAIL11.9s
CG-AL-H007hard2100.0 / 10010/10OK3m 26s
CG-AL-H008hard20.0 / 1000/0FAIL17.5s
CG-AL-H009hard1100.0 / 10011/11OK3m 0s
CG-AL-H010hard2100.0 / 1008/8OK3m 37s
CG-AL-H011hard20.0 / 1000/0FAIL15.8s
CG-AL-H013hard1100.0 / 1009/9OK3m 17s
CG-AL-H014hard20.0 / 1000/0FAIL11.3s
CG-AL-H015hard1100.0 / 1004/4OK3m 5s
CG-AL-H016hard20.0 / 1000/0FAIL10.8s
CG-AL-H017hard20.0 / 1000/0FAIL20.7s
CG-AL-H018hard20.0 / 1000/0FAIL10.8s
CG-AL-H019hard20.0 / 1000/0FAIL10.7s
CG-AL-H020hard20.0 / 1000/0FAIL10.9s
CG-AL-H021hard20.0 / 1000/0FAIL11.0s
CG-AL-H022hard20.0 / 1000/0FAIL11.2s
CG-AL-H023hard20.0 / 1000/0FAIL11.7s
CG-AL-H024hard20.0 / 1000/0FAIL10.9s
CG-AL-H025hard1100.0 / 1007/7OK2m 48s
CG-AL-H026hard20.0 / 1000/0FAIL10.8s
CG-AL-H205hard20.0 / 1000/0FAIL10.9s
CG-AL-M001medium20.0 / 1000/0FAIL10.7s
CG-AL-M002medium20.0 / 1000/0FAIL20.8s
CG-AL-M003medium20.0 / 1000/0FAIL1m 44s
CG-AL-M004medium20.0 / 1000/0FAIL3m 2s
CG-AL-M005medium20.0 / 1000/0FAIL10.9s
CG-AL-M006medium20.0 / 1000/0FAIL10.8s
CG-AL-M007medium20.0 / 1000/0FAIL10.8s
CG-AL-M008medium20.0 / 1000/0FAIL2m 29s
CG-AL-M009medium20.0 / 1000/0FAIL12.2s
CG-AL-M010medium20.0 / 1000/0FAIL11.3s
CG-AL-M020medium20.0 / 1000/0FAIL10.9s
CG-AL-M021medium20.0 / 1000/0FAIL1m 20s
CG-AL-M022medium262.5 / 1007/9OK3m 31s
CG-AL-M023medium20.0 / 1000/0FAIL10.9s
CG-AL-M024medium20.0 / 1000/0FAIL10.9s
CG-AL-M025medium20.0 / 1000/0FAIL10.8s
CG-AL-M026medium20.0 / 1000/0FAIL48.9s
CG-AL-M088medium20.0 / 1000/0FAIL1m 3s
CG-AL-M112medium262.5 / 1002/4OK3m 49s