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.

70.3% 45/64 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.

59.1 / 100
Cost $1.15
Tokens 60k / 67k input / output, all attempts
Duration 2h 35m
Filter:
Per-task results for run 886e8916-8c05-4a9e-8e2e-7c1cf215412d
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 21s258 / 188
CG-AL-E002easy1100.0 / 1006/6OK2m 25s272 / 184
CG-AL-E003easy1100.0 / 1005/5OK2m 19s259 / 101
CG-AL-E004easy1100.0 / 1006/6OK2m 22s279 / 191
CG-AL-E005easy1100.0 / 10013/13OK2m 25s293 / 425
CG-AL-E006easy1100.0 / 1007/7OK2m 27s284 / 294
CG-AL-E007easy1100.0 / 1007/7OK2m 29s345 / 126
CG-AL-E008easy20.0 / 1000/0FAIL6.8s1.0k / 505
CG-AL-E009easy1100.0 / 1005/5OK2m 27s271 / 137
CG-AL-E010easy1100.0 / 1005/5OK2m 27s275 / 92
CG-AL-E031easy1100.0 / 1003/3OK2m 29s401 / 334
CG-AL-E032easy20.0 / 1000/0FAIL5.5s710 / 93
CG-AL-E045easy1100.0 / 1004/4OK2m 23s360 / 288
CG-AL-E050easy20.0 / 1000/0FAIL6.4s1.8k / 307
CG-AL-E051easy1100.0 / 10015/15OK2m 26s455 / 881
CG-AL-E052easy2100.0 / 10016/16OK2m 19s905 / 450
CG-AL-E053easy1100.0 / 1003/3OK2m 19s293 / 106
CG-AL-E054easy2100.0 / 1009/9OK2m 18s1.0k / 385
CG-AL-E055easy2100.0 / 1008/8OK2m 19s876 / 358
CG-AL-H001easy1100.0 / 10025/25OK2m 22s453 / 354
CG-AL-H002easy1100.0 / 1004/4OK2m 20s425 / 465
CG-AL-H003easy262.5 / 1004/5OK2m 23s1.4k / 1.1k
CG-AL-H004easy1100.0 / 10014/14OK2m 21s474 / 377
CG-AL-H005easy262.5 / 1002/5OK2m 24s2.0k / 1.6k
CG-AL-H006easy1100.0 / 1006/6OK2m 18s421 / 207
CG-AL-H007easy2100.0 / 10010/10OK2m 20s1.6k / 958
CG-AL-H008easy1100.0 / 10010/10OK2m 20s504 / 309
CG-AL-H009easy1100.0 / 10011/11OK2m 22s574 / 616
CG-AL-H010easy1100.0 / 1008/8OK2m 19s493 / 321
CG-AL-H011easy20.0 / 1000/0FAIL6.6s928 / 305
CG-AL-H013easy1100.0 / 1009/9OK2m 19s358 / 278
CG-AL-H014easy20.0 / 1000/0FAIL11.1s1.5k / 968
CG-AL-H015easy1100.0 / 1004/4OK2m 19s387 / 236
CG-AL-H016easy262.5 / 1003/4OK2m 19s1.0k / 458
CG-AL-H017easy20.0 / 1000/0FAIL6.5s942 / 406
CG-AL-H018easy1100.0 / 1006/6OK2m 23s420 / 486
CG-AL-H019easy2100.0 / 1005/5OK2m 16s817 / 274
CG-AL-H020easy2100.0 / 10010/10OK2m 25s2.1k / 1.5k
CG-AL-H021easy262.5 / 1006/20OK2m 24s1.9k / 1.2k
CG-AL-H022easy1100.0 / 10021/21OK2m 26s724 / 817
CG-AL-H023easy20.0 / 1000/0FAIL41.9s3.5k / 7.5k
CG-AL-H024easy1100.0 / 1009/9OK2m 26s508 / 706
CG-AL-H025easy2100.0 / 1007/7OK2m 21s1.9k / 372
CG-AL-H026easy1100.0 / 1008/8OK2m 19s443 / 296
CG-AL-H205easy1100.0 / 1006/6OK2m 21s434 / 328
CG-AL-M001easy262.5 / 1005/10OK2m 22s1.4k / 1.2k
CG-AL-M002easy1100.0 / 10022/22OK2m 21s403 / 451
CG-AL-M003easy262.5 / 1008/9OK2m 23s1.7k / 1.4k
CG-AL-M004easy1100.0 / 10012/12OK2m 33s449 / 923
CG-AL-M005easy20.0 / 1000/0FAIL18.3s2.1k / 3.7k
CG-AL-M006easy1100.0 / 10018/18OK2m 33s408 / 1.5k
CG-AL-M007easy262.5 / 10013/15OK2m 58s2.0k / 7.1k
CG-AL-M008easy2100.0 / 10012/12OK2m 53s2.0k / 7.1k
CG-AL-M009easy20.0 / 1000/0FAIL30.2s2.0k / 5.3k
CG-AL-M010easy262.5 / 10019/21OK2m 34s2.1k / 3.5k
CG-AL-M020easy2100.0 / 10017/17OK2m 21s1.9k / 1.3k
CG-AL-M021easy1100.0 / 10011/11OK2m 20s547 / 466
CG-AL-M022easy2100.0 / 1009/9OK2m 23s1.7k / 1.2k
CG-AL-M023easy1100.0 / 10011/11OK2m 20s482 / 412
CG-AL-M024easy1100.0 / 10010/10OK2m 25s477 / 855
CG-AL-M025easy262.5 / 1000/0OK2m 17s1.1k / 589
CG-AL-M026easy1100.0 / 1008/8OK2m 21s370 / 404
CG-AL-M088easy1100.0 / 1006/6OK2m 19s391 / 353
CG-AL-M112easy262.5 / 1002/4OK2m 24s1.7k / 1.2k