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.

58.2% 64/110 of 110 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.

43.9 / 100
Cost $0.72
Tokens 156k / 113k input / output, all attempts
Duration 1h 18m
Filter:
Per-task results for run 01e4c1c3-08b2-4668-9ab2-74a39d944662
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK15.2s272 / 239
CG-AL-E002easy1100.0 / 1006/6OK2m 20s285 / 302
CG-AL-E003easy1100.0 / 1005/5OK18.4s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK23.8s300 / 336
CG-AL-E005easy2100.0 / 10013/13OK38.7s1.5k / 1.0k
CG-AL-E006easy2100.0 / 1007/7OK2m 57s1.1k / 896
CG-AL-E007easy2100.0 / 1007/7OK34.4s1.1k / 397
CG-AL-E008easy1100.0 / 1006/6OK41.7s291 / 304
CG-AL-E009easy1100.0 / 1005/5OK44.9s285 / 164
CG-AL-E010easy1100.0 / 1005/5OK48.9s296 / 116
CG-AL-E031easy1100.0 / 1003/3OK50.3s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK49.1s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK15.3s385 / 361
CG-AL-E050easy20.0 / 1000/0FAIL8.5s2.2k / 451
CG-AL-E051easy262.5 / 1003/15OK21.8s6.1k / 1.9k
CG-AL-E052easy2100.0 / 10016/16OK15.1s1.7k / 570
CG-AL-E053easy2100.0 / 1003/3OK2m 17s830 / 303
CG-AL-E054easy20.0 / 1000/0FAIL6.2s1.2k / 490
CG-AL-E055easy1100.0 / 1008/8OK14.7s385 / 218
CG-AL-E056easy20.0 / 1000/0FAIL7.2s1.9k / 688
CG-AL-E057easy20.0 / 1000/0FAIL6.6s1.7k / 770
CG-AL-E058easy2100.0 / 1001/1OK15.6s988 / 231
CG-AL-H001hard1100.0 / 10025/25OK15.0s491 / 447
CG-AL-H002hard2100.0 / 1004/4OK14.3s1.7k / 1.1k
CG-AL-H003hard1100.0 / 1005/5OK17.2s524 / 657
CG-AL-H004hard1100.0 / 10014/14OK16.0s535 / 437
CG-AL-H005hard2100.0 / 1006/6OK15.8s2.3k / 1.3k
CG-AL-H006hard1100.0 / 1006/6OK14.2s454 / 243
CG-AL-H007hard2100.0 / 10010/10OK15.5s2.0k / 1.3k
CG-AL-H008hard20.0 / 1000/0FAIL9.0s2.1k / 1.8k
CG-AL-H009hard1100.0 / 10011/11OK18.1s688 / 811
CG-AL-H010hard1100.0 / 1008/8OK15.2s561 / 406
CG-AL-H011hard20.0 / 1000/0FAIL6.0s1.4k / 430
CG-AL-H013hard1100.0 / 1009/9OK14.8s392 / 339
CG-AL-H014hard20.0 / 1000/0FAIL6.9s1.6k / 884
CG-AL-H015hard1100.0 / 1004/4OK14.6s443 / 312
CG-AL-H016hard20.0 / 1000/0FAIL6.4s1.3k / 632
CG-AL-H017hard20.0 / 1000/0FAIL6.8s1.3k / 616
CG-AL-H018hard20.0 / 1000/0FAIL7.7s1.7k / 987
CG-AL-H019hard2100.0 / 1005/5OK14.3s955 / 343
CG-AL-H020hard262.5 / 1009/10OK17.4s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL9.5s3.1k / 1.7k
CG-AL-H022hard262.5 / 10017/21OK17.1s2.8k / 1.9k
CG-AL-H023hard20.0 / 1000/0FAIL22.1s4.0k / 7.3k
CG-AL-H024hard1100.0 / 1009/9OK29.9s573 / 1.0k
CG-AL-H025hard1100.0 / 1007/7OK14.4s388 / 272
CG-AL-H026hard1100.0 / 1008/8OK15.1s509 / 364
CG-AL-H027hard262.5 / 1002/4OK17.7s2.6k / 826
CG-AL-H028hard1100.0 / 1009/9OK27.7s692 / 573
CG-AL-H029hard20.0 / 1000/0FAIL11.5s3.4k / 2.3k
CG-AL-H030hard20.0 / 1000/0FAIL8.3s2.4k / 1.4k
CG-AL-H031hard1100.0 / 10022/22OK17.8s1.1k / 1.1k
CG-AL-H032hard2100.0 / 10019/19OK19.9s2.8k / 2.0k
CG-AL-H033hard1100.0 / 1005/5OK2m 38s823 / 1.5k
CG-AL-H034hard2100.0 / 1003/3OK14.1s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK14.9s317 / 102
CG-AL-H036hard20.0 / 1000/0FAIL5.9s1.3k / 327
CG-AL-H037hard20.0 / 1000/0FAIL6.3s1.6k / 390
CG-AL-H038hard20.0 / 1000/0FAIL6.6s1.7k / 615
CG-AL-H039hard1100.0 / 1004/4OK14.3s524 / 273
CG-AL-H040hard1100.0 / 1002/2OK14.0s430 / 174
CG-AL-H041hard20.0 / 1000/0FAIL7.8s2.1k / 1.2k
CG-AL-H042hard20.0 / 1000/0FAIL5.8s1.1k / 301
CG-AL-H043hard1100.0 / 1005/5OK13.6s430 / 99
CG-AL-H050hard262.5 / 1002/3OK14.1s1.6k / 377
CG-AL-H051hard1100.0 / 1004/4OK14.5s695 / 208
CG-AL-H052hard1100.0 / 1005/5OK15.1s784 / 220
CG-AL-H053hard2100.0 / 1004/4OK13.8s1.5k / 533
CG-AL-H054hard2100.0 / 1005/5OK16.9s2.4k / 1.3k
CG-AL-H056hard20.0 / 1000/0FAIL7.2s1.7k / 330
CG-AL-H057hard1100.0 / 1004/4OK2m 25s776 / 392
CG-AL-H058hard1100.0 / 1005/5OK15.0s644 / 325
CG-AL-H205hard2100.0 / 1006/6OK28.3s1.9k / 1.1k
CG-AL-M001medium20.0 / 1000/0FAIL7.3s1.9k / 1.1k
CG-AL-M002medium262.5 / 10021/22OK18.5s4.0k / 2.0k
CG-AL-M003medium20.0 / 1000/0FAIL8.7s1.9k / 1.7k
CG-AL-M004medium1100.0 / 10012/12OK2m 30s496 / 1.0k
CG-AL-M005medium20.0 / 1000/0FAIL14.2s2.3k / 3.6k
CG-AL-M006medium20.0 / 1000/0FAIL10.6s2.1k / 2.5k
CG-AL-M007medium20.0 / 1000/0FAIL16.2s3.1k / 5.2k
CG-AL-M008medium20.0 / 1000/0FAIL1m 37s3.3k / 6.0k
CG-AL-M009medium2100.0 / 10011/11OK3m 16s2.2k / 6.9k
CG-AL-M010medium262.5 / 10020/21OK3m 40s2.6k / 4.0k
CG-AL-M020medium2100.0 / 10017/17OK40.7s3.2k / 1.9k
CG-AL-M021medium20.0 / 1000/0FAIL53.0s2.1k / 1.1k
CG-AL-M022medium1100.0 / 1009/9OK18.2s554 / 811
CG-AL-M023medium262.5 / 10010/11OK16.5s1.9k / 1.1k
CG-AL-M024medium20.0 / 1000/0FAIL19.0s2.8k / 2.5k
CG-AL-M025medium262.5 / 1002/7OK14.2s1.4k / 780
CG-AL-M026medium1100.0 / 1008/8OK16.2s426 / 347
CG-AL-M027medium20.0 / 1000/0FAIL15.2s3.9k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK2m 19s1.2k / 610
CG-AL-M029medium2100.0 / 1003/3OK2m 17s999 / 220
CG-AL-M031medium20.0 / 1000/0FAIL8.6s2.1k / 1.7k
CG-AL-M032medium10.0 / 1000/0FAIL0ms0 / 0
CG-AL-M033medium2100.0 / 1002/2OK14.7s1.3k / 529
CG-AL-M034medium262.5 / 1001/2OK18.2s1.5k / 512
CG-AL-M035medium1100.0 / 1002/2OK13.5s358 / 98
CG-AL-M036medium20.0 / 1000/0FAIL7.1s1.7k / 633
CG-AL-M037medium20.0 / 1000/0FAIL6.8s1.5k / 504
CG-AL-M038medium1100.0 / 1002/2OK13.8s433 / 186
CG-AL-M039medium1100.0 / 1002/2OK2m 18s502 / 369
CG-AL-M040medium262.5 / 1001/2OK13.6s907 / 359
CG-AL-M041medium20.0 / 1000/0FAIL5.6s844 / 238
CG-AL-M042medium2100.0 / 1008/8OK22.4s3.0k / 1.3k
CG-AL-M043medium262.5 / 1000/5OK13.9s1.4k / 542
CG-AL-M044medium1100.0 / 1006/6OK2m 20s719 / 650
CG-AL-M045medium1100.0 / 1006/6OK14.1s776 / 259
CG-AL-M088medium1100.0 / 1006/6OK14.9s451 / 429
CG-AL-M112medium2100.0 / 1004/4OK16.7s2.2k / 1.5k