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.

32.8% 21/64 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.

21.9 / 100
Cost $0.84
Tokens 56k / 214k input / output, all attempts
Duration 3h 13m
Filter:
Per-task results for run 3b640f0a-4329-4394-a363-f981586e5d1a
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 53s259 / 742
CG-AL-E002easy2100.0 / 1006/6OK3m 14s1.0k / 2.4k
CG-AL-E003easy1100.0 / 1005/5OK2m 47s260 / 611
CG-AL-E004easy1100.0 / 1006/6OK2m 55s281 / 1.0k
CG-AL-E005easy262.5 / 10011/13OK3m 14s1.1k / 3.9k
CG-AL-E006easy2100.0 / 1007/7OK3m 22s968 / 4.5k
CG-AL-E007easy20.0 / 1000/0FAIL1m 16s989 / 4.3k
CG-AL-E008easy20.0 / 1000/0FAIL1m 0s1.0k / 3.1k
CG-AL-E009easy20.0 / 1000/0FAIL26.8s776 / 2.4k
CG-AL-E010easy20.0 / 1000/0FAIL43.8s687 / 1.8k
CG-AL-E031easy1100.0 / 1003/3OK3m 22s398 / 1.3k
CG-AL-E032easy1100.0 / 1001/1OK2m 56s222 / 262
CG-AL-E045easy1100.0 / 1004/4OK3m 48s362 / 3.0k
CG-AL-E050easy20.0 / 1000/0FAIL1m 39s1.9k / 5.8k
CG-AL-E051easy20.0 / 1000/0FAIL2m 34s2.2k / 13k
CG-AL-E052easy2100.0 / 10016/16OK4m 58s981 / 5.9k
CG-AL-E053easy20.0 / 1000/0FAIL42.3s345 / 1.2k
CG-AL-E054easy20.0 / 1000/0FAIL53.5s355 / 1.5k
CG-AL-E055easy2100.0 / 1008/8OK2m 47s324 / 757
CG-AL-H001hard1100.0 / 10025/25OK3m 9s454 / 1.1k
CG-AL-H002hard2100.0 / 1004/4OK2m 43s1.5k / 3.1k
CG-AL-H003hard20.0 / 1000/0FAIL11.6s468 / 2.4k
CG-AL-H004hard1100.0 / 10014/14OK2m 54s483 / 424
CG-AL-H005hard20.0 / 1000/0FAIL1m 9s1.8k / 4.8k
CG-AL-H006hard1100.0 / 1006/6OK2m 45s421 / 742
CG-AL-H007hard1100.0 / 10010/10OK3m 45s550 / 3.6k
CG-AL-H008hard2100.0 / 10010/10OK2m 38s1.5k / 2.9k
CG-AL-H009hard20.0 / 1000/0FAIL51.6s1.8k / 4.7k
CG-AL-H010hard20.0 / 1000/0FAIL44.1s1.4k / 3.1k
CG-AL-H011hard20.0 / 1000/0FAIL56.9s1.1k / 5.0k
CG-AL-H013hard2100.0 / 1009/9OK2m 49s1.2k / 1.8k
CG-AL-H014hard20.0 / 1000/0FAIL33.1s422 / 363
CG-AL-H015hard2100.0 / 1004/4OK2m 45s370 / 259
CG-AL-H016hard20.0 / 1000/0FAIL11.6s385 / 361
CG-AL-H017hard20.0 / 1000/0FAIL10.7s0 / 0
CG-AL-H018hard20.0 / 1000/0FAIL33.7s1.4k / 870
CG-AL-H019hard20.0 / 1000/0FAIL10.9s316 / 1.2k
CG-AL-H020hard20.0 / 1000/0FAIL10.8s0 / 0
CG-AL-H021hard20.0 / 1000/0FAIL11.0s0 / 0
CG-AL-H022hard20.0 / 1000/0FAIL46.8s2.5k / 3.7k
CG-AL-H023hard20.0 / 1000/0FAIL13.4s1.2k / 16k
CG-AL-H024hard20.0 / 1000/0FAIL12.3s506 / 973
CG-AL-H025hard20.0 / 1000/0FAIL19.9s339 / 218
CG-AL-H026hard20.0 / 1000/0FAIL11.9s443 / 1.7k
CG-AL-H205hard2100.0 / 1006/6OK2m 47s1.4k / 2.2k
CG-AL-M001medium20.0 / 1000/0FAIL1m 15s2.1k / 3.2k
CG-AL-M002medium20.0 / 1000/0FAIL12.0s410 / 923
CG-AL-M003medium262.5 / 1008/9OK3m 35s1.5k / 4.5k
CG-AL-M004medium20.0 / 1000/0FAIL22.8s460 / 3.7k
CG-AL-M005medium20.0 / 1000/0FAIL3m 37s2.3k / 13k
CG-AL-M006medium20.0 / 1000/0FAIL12.2s409 / 7.0k
CG-AL-M007medium20.0 / 1000/0FAIL2m 43s330 / 2.5k
CG-AL-M008medium20.0 / 1000/0FAIL3m 42s1.9k / 14k
CG-AL-M009medium20.0 / 1000/0FAIL12.2s432 / 4.9k
CG-AL-M010medium20.0 / 1000/0FAIL2m 14s2.8k / 4.3k
CG-AL-M020medium20.0 / 1000/0FAIL11.0s0 / 0
CG-AL-M021medium20.0 / 1000/0FAIL3m 2s481 / 1.5k
CG-AL-M022medium20.0 / 1000/0FAIL56.0s479 / 646
CG-AL-M023medium1100.0 / 10011/11OK3m 12s486 / 477
CG-AL-M024medium20.0 / 1000/0FAIL2m 27s2.5k / 8.2k
CG-AL-M025medium262.5 / 1002/7OK3m 7s389 / 324
CG-AL-M026medium20.0 / 1000/0FAIL1m 15s354 / 2.4k
CG-AL-M088medium1100.0 / 1006/6OK2m 33s397 / 341
CG-AL-M112medium262.5 / 1002/4OK11m 33s1.6k / 24k