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.

23.9 / 100
Cost $0.39
Tokens 115k / 389k input / output, all attempts
Duration 4h 45m
Filter:
Per-task results for run 0a7fca96-9d44-4436-bf17-6edf802ef66b
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK3m 0s259 / 1.2k
CG-AL-E002easy20.0 / 1000/0FAIL1m 23s906 / 3.5k
CG-AL-E003easy1100.0 / 1005/5OK2m 37s260 / 534
CG-AL-E004easy1100.0 / 1006/6OK2m 41s281 / 623
CG-AL-E005easy20.0 / 1000/0FAIL37.2s1.1k / 2.8k
CG-AL-E006easy20.0 / 1000/0FAIL1m 5s944 / 4.9k
CG-AL-E007easy1100.0 / 1007/7OK3m 6s347 / 637
CG-AL-E008easy20.0 / 1000/0FAIL1m 20s1.0k / 2.8k
CG-AL-E009easy20.0 / 1000/0FAIL46.9s1.6k / 2.8k
CG-AL-E010easy2100.0 / 1005/5OK5m 41s1.1k / 6.8k
CG-AL-E031easy1100.0 / 1003/3OK3m 44s398 / 752
CG-AL-E032easy1100.0 / 1001/1OK3m 14s222 / 340
CG-AL-E045easy1100.0 / 1004/4OK2m 41s362 / 1.5k
CG-AL-E050easy20.0 / 1000/0FAIL31.7s1.9k / 1.5k
CG-AL-E051easy20.0 / 1000/0FAIL1m 53s2.2k / 7.4k
CG-AL-E052easy262.5 / 10014/16OK4m 11s2.1k / 7.1k
CG-AL-E053easy20.0 / 1000/0FAIL1m 35s1.2k / 3.9k
CG-AL-E054easy20.0 / 1000/0FAIL1m 14s1.3k / 2.9k
CG-AL-E055easy1100.0 / 1008/8OK2m 46s343 / 712
CG-AL-H001easy1100.0 / 10025/25OK3m 20s454 / 1.9k
CG-AL-H002easy2100.0 / 1004/4OK3m 52s1.6k / 3.0k
CG-AL-H003easy262.5 / 1003/5OK4m 3s1.4k / 4.9k
CG-AL-H004easy2100.0 / 10014/14OK2m 40s1.6k / 1.9k
CG-AL-H005easy20.0 / 1000/0FAIL2m 6s1.8k / 6.2k
CG-AL-H006easy1100.0 / 1006/6OK3m 19s421 / 963
CG-AL-H007easy1100.0 / 10010/10OK4m 7s550 / 3.5k
CG-AL-H008easy20.0 / 1000/0FAIL42.2s1.5k / 3.3k
CG-AL-H009easy1100.0 / 10011/11OK3m 33s583 / 1.7k
CG-AL-H010easy1100.0 / 1008/8OK5m 17s1.0k / 3.7k
CG-AL-H011easy20.0 / 1000/0FAIL5m 37s2.4k / 13k
CG-AL-H013easy1100.0 / 1009/9OK3m 2s360 / 1.4k
CG-AL-H014easy20.0 / 1000/0FAIL44.3s1.4k / 3.3k
CG-AL-H015easy2100.0 / 1004/4OK2m 41s1.5k / 13k
CG-AL-H016easy20.0 / 1000/0FAIL2m 6s1.0k / 6.2k
CG-AL-H017easy20.0 / 1000/0FAIL43.9s969 / 4.0k
CG-AL-H018easy20.0 / 1000/0FAIL2m 13s3.6k / 9.8k
CG-AL-H019easy20.0 / 1000/0FAIL58.8s875 / 2.9k
CG-AL-H020easy20.0 / 1000/0FAIL53.0s1.9k / 5.2k
CG-AL-H021easy20.0 / 1000/0FAIL3m 15s2.9k / 7.5k
CG-AL-H022easy20.0 / 1000/0FAIL5m 3s4.8k / 12k
CG-AL-H023easy20.0 / 1000/0FAIL8m 25s10k / 24k
CG-AL-H024easy20.0 / 1000/0FAIL3m 10s3.0k / 9.5k
CG-AL-H025easy2100.0 / 1007/7OK2m 58s1.0k / 2.4k
CG-AL-H026easy20.0 / 1000/0FAIL46.1s1.5k / 2.9k
CG-AL-H205easy20.0 / 1000/0FAIL1m 2s1.3k / 3.2k
CG-AL-M001easy20.0 / 1000/0FAIL5m 11s3.5k / 14k
CG-AL-M002easy20.0 / 1000/0FAIL2m 5s1.3k / 6.8k
CG-AL-M003easy262.5 / 1008/9OK3m 55s1.6k / 6.8k
CG-AL-M004easy20.0 / 1000/0FAIL1m 1s1.7k / 5.8k
CG-AL-M005easy20.0 / 1000/0FAIL4m 2s2.8k / 16k
CG-AL-M006easy20.0 / 1000/0FAIL1m 17s1.7k / 5.8k
CG-AL-M007easy20.0 / 1000/0FAIL6m 48s5.9k / 25k
CG-AL-M008easy20.0 / 1000/0FAIL3m 56s3.0k / 24k
CG-AL-M009easy2100.0 / 10011/11OK7m 41s4.6k / 11k
CG-AL-M010easy20.0 / 1000/0FAIL1m 49s2.6k / 8.1k
CG-AL-M020easy20.0 / 1000/0FAIL32.8s2.4k / 7.5k
CG-AL-M021easy20.0 / 1000/0FAIL1m 22s1.8k / 5.0k
CG-AL-M022easy20.0 / 1000/0FAIL1m 9s2.1k / 5.1k
CG-AL-M023easy20.0 / 1000/0FAIL33.0s1.5k / 3.4k
CG-AL-M024easy20.0 / 1000/0FAIL1m 28s2.4k / 5.5k
CG-AL-M025easy20.0 / 1000/0FAIL7m 56s2.6k / 11k
CG-AL-M026easy262.5 / 1006/8OK5m 19s1.1k / 6.3k
CG-AL-M088easy2100.0 / 1006/6OK2m 57s1.3k / 3.0k
CG-AL-M112easy20.0 / 1000/0FAIL6m 22s3.8k / 15k