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.

40.6% 26/64 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.

29.0 / 100
Cost $0.34
Tokens 98k / 338k input / output, all attempts
Duration 4h 38m
Filter:
Per-task results for run d29122fc-9975-48cf-8d8e-02d4fdd77888
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK3m 39s1.1k / 2.7k
CG-AL-E002easy1100.0 / 1006/6OK2m 59s273 / 1.3k
CG-AL-E003easy1100.0 / 1005/5OK2m 31s260 / 368
CG-AL-E004easy1100.0 / 1006/6OK2m 53s281 / 1.1k
CG-AL-E005easy20.0 / 1000/0FAIL1m 22s1.0k / 3.0k
CG-AL-E006easy20.0 / 1000/0FAIL1m 16s946 / 3.4k
CG-AL-E007easy1100.0 / 1007/7OK3m 35s347 / 948
CG-AL-E008easy20.0 / 1000/0FAIL38.3s1.1k / 1.7k
CG-AL-E009easy1100.0 / 1005/5OK3m 37s271 / 1.6k
CG-AL-E010easy20.0 / 1000/0FAIL54.9s686 / 1.7k
CG-AL-E031easy1100.0 / 1003/3OK5m 13s796 / 5.4k
CG-AL-E032easy2100.0 / 1001/1OK3m 34s717 / 2.6k
CG-AL-E045easy1100.0 / 1004/4OK3m 46s362 / 1.9k
CG-AL-E050easy20.0 / 1000/0FAIL1m 12s2.1k / 2.3k
CG-AL-E051easy20.0 / 1000/0FAIL2m 5s2.4k / 7.1k
CG-AL-E052easy20.0 / 1000/0FAIL6m 5s2.0k / 13k
CG-AL-E053easy1100.0 / 1003/3OK2m 47s293 / 843
CG-AL-E054easy20.0 / 1000/0FAIL44.5s1.2k / 2.6k
CG-AL-E055easy1100.0 / 1008/8OK2m 45s343 / 783
CG-AL-H001easy1100.0 / 10025/25OK3m 14s454 / 1.2k
CG-AL-H002easy2100.0 / 1004/4OK2m 40s1.5k / 1.9k
CG-AL-H003easy262.5 / 1004/5OK5m 47s2.4k / 8.2k
CG-AL-H004easy1100.0 / 10014/14OK3m 5s483 / 1.5k
CG-AL-H005easy20.0 / 1000/0FAIL1m 50s1.9k / 4.9k
CG-AL-H006easy1100.0 / 1006/6OK2m 59s421 / 892
CG-AL-H007easy20.0 / 1000/0FAIL46.0s1.6k / 4.0k
CG-AL-H008easy2100.0 / 10010/10OK2m 44s1.5k / 2.2k
CG-AL-H009easy1100.0 / 10011/11OK3m 53s583 / 1.4k
CG-AL-H010easy2100.0 / 1008/8OK3m 40s1.4k / 4.6k
CG-AL-H011easy20.0 / 1000/0FAIL3m 44s2.2k / 14k
CG-AL-H013easy1100.0 / 1009/9OK2m 51s360 / 885
CG-AL-H014easy20.0 / 1000/0FAIL1m 59s2.5k / 5.8k
CG-AL-H015easy1100.0 / 1004/4OK2m 56s389 / 1.0k
CG-AL-H016easy20.0 / 1000/0FAIL1m 47s1.3k / 4.8k
CG-AL-H017easy20.0 / 1000/0FAIL1m 8s1.3k / 4.9k
CG-AL-H018easy20.0 / 1000/0FAIL51.6s2.8k / 14k
CG-AL-H019easy20.0 / 1000/0FAIL2m 16s1.4k / 7.1k
CG-AL-H020easy20.0 / 1000/0FAIL3m 50s5.4k / 9.8k
CG-AL-H021easy20.0 / 1000/0FAIL1m 23s2.3k / 5.0k
CG-AL-H022easy20.0 / 1000/0FAIL2m 42s1.7k / 9.1k
CG-AL-H023easy20.0 / 1000/0FAIL4m 11s4.0k / 17k
CG-AL-H024easy20.0 / 1000/0FAIL56.7s2.6k / 4.1k
CG-AL-H025easy20.0 / 1000/0FAIL54.7s1.1k / 2.4k
CG-AL-H026easy1100.0 / 1008/8OK2m 55s443 / 987
CG-AL-H205easy2100.0 / 1006/6OK3m 35s1.2k / 2.4k
CG-AL-M001easy20.0 / 1000/0FAIL2m 6s1.3k / 4.4k
CG-AL-M002easy20.0 / 1000/0FAIL1m 32s1.7k / 4.6k
CG-AL-M003easy262.5 / 1008/9OK2m 54s1.4k / 5.1k
CG-AL-M004easy20.0 / 1000/0FAIL3m 18s3.6k / 9.1k
CG-AL-M005easy20.0 / 1000/0FAIL7m 21s6.5k / 19k
CG-AL-M006easy20.0 / 1000/0FAIL1m 21s1.6k / 10k
CG-AL-M007easy20.0 / 1000/0FAIL4m 39s2.6k / 19k
CG-AL-M008easy20.0 / 1000/0FAIL4m 46s2.1k / 16k
CG-AL-M009easy2100.0 / 10011/11OK4m 59s1.9k / 8.5k
CG-AL-M010easy20.0 / 1000/0FAIL2m 12s2.6k / 12k
CG-AL-M020easy20.0 / 1000/0FAIL1m 12s2.0k / 3.8k
CG-AL-M021easy20.0 / 1000/0FAIL1m 14s1.9k / 3.6k
CG-AL-M022easy20.0 / 1000/0FAIL1m 31s2.0k / 15k
CG-AL-M023easy1100.0 / 10011/11OK3m 11s486 / 1.4k
CG-AL-M024easy20.0 / 1000/0FAIL1m 22s2.4k / 4.5k
CG-AL-M025easy262.5 / 1002/7OK4m 59s1.2k / 6.2k
CG-AL-M026easy1100.0 / 1008/8OK2m 59s373 / 1.4k
CG-AL-M088easy1100.0 / 1006/6OK3m 20s397 / 1.9k
CG-AL-M112easy262.5 / 1002/4OK3m 23s2.7k / 4.7k