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.

61.8% 68/110 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.

45.6 / 100
Cost $0.72
Tokens 161k / 111k input / output, all attempts
Duration 1h 16m
Filter:
Per-task results for run 2fff6752-91c5-4d88-9560-c34647d29135
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK38.8s272 / 239
CG-AL-E002easy1100.0 / 1006/6OK3m 17s285 / 302
CG-AL-E003easy1100.0 / 1005/5OK40.3s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK34.0s300 / 336
CG-AL-E005easy2100.0 / 10013/13OK31.3s1.4k / 970
CG-AL-E006easy1100.0 / 1007/7OK3m 7s301 / 433
CG-AL-E007easy2100.0 / 1007/7OK27.8s1.1k / 397
CG-AL-E008easy1100.0 / 1006/6OK42.8s291 / 304
CG-AL-E009easy1100.0 / 1005/5OK46.8s285 / 164
CG-AL-E010easy1100.0 / 1005/5OK49.4s296 / 116
CG-AL-E031easy1100.0 / 1003/3OK51.6s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK49.9s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK15.6s385 / 333
CG-AL-E050easy20.0 / 1000/0FAIL7.4s2.2k / 451
CG-AL-E051easy2100.0 / 10015/15OK20.2s5.1k / 1.5k
CG-AL-E052easy2100.0 / 10016/16OK14.9s1.7k / 570
CG-AL-E053easy2100.0 / 1003/3OK2m 41s829 / 303
CG-AL-E054easy20.0 / 1000/0FAIL6.5s1.2k / 490
CG-AL-E055easy1100.0 / 1008/8OK15.7s385 / 218
CG-AL-E056easy262.5 / 10010/15OK16.0s2.1k / 916
CG-AL-E057easy20.0 / 1000/0FAIL9.9s1.7k / 770
CG-AL-E058easy2100.0 / 1001/1OK14.9s992 / 231
CG-AL-H001hard1100.0 / 10025/25OK16.6s491 / 447
CG-AL-H002hard2100.0 / 1004/4OK16.5s1.7k / 1.0k
CG-AL-H003hard1100.0 / 1005/5OK17.8s524 / 655
CG-AL-H004hard1100.0 / 10014/14OK16.1s535 / 437
CG-AL-H005hard20.0 / 1000/0FAIL7.6s2.3k / 1.3k
CG-AL-H006hard1100.0 / 1006/6OK14.7s454 / 247
CG-AL-H007hard2100.0 / 10010/10OK17.0s2.0k / 1.3k
CG-AL-H008hard20.0 / 1000/0FAIL8.8s2.2k / 1.8k
CG-AL-H009hard1100.0 / 10011/11OK18.1s688 / 944
CG-AL-H010hard1100.0 / 1008/8OK15.9s561 / 406
CG-AL-H011hard20.0 / 1000/0FAIL6.3s1.4k / 430
CG-AL-H013hard1100.0 / 1009/9OK22.1s392 / 339
CG-AL-H014hard20.0 / 1000/0FAIL7.2s1.6k / 884
CG-AL-H015hard1100.0 / 1004/4OK16.7s443 / 312
CG-AL-H016hard20.0 / 1000/0FAIL7.1s1.3k / 632
CG-AL-H017hard20.0 / 1000/0FAIL6.8s1.2k / 530
CG-AL-H018hard2100.0 / 1006/6OK15.2s1.7k / 957
CG-AL-H019hard2100.0 / 1005/5OK14.8s955 / 343
CG-AL-H020hard20.0 / 1000/0FAIL9.3s2.5k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL9.3s3.0k / 1.7k
CG-AL-H022hard262.5 / 10017/21OK18.6s2.7k / 1.9k
CG-AL-H023hard20.0 / 1000/0FAIL41.7s6.6k / 9.2k
CG-AL-H024hard1100.0 / 1009/9OK29.1s573 / 1.0k
CG-AL-H025hard1100.0 / 1007/7OK47.3s388 / 267
CG-AL-H026hard1100.0 / 1008/8OK15.9s509 / 364
CG-AL-H027hard2100.0 / 1004/4OK16.7s2.6k / 803
CG-AL-H028hard1100.0 / 1009/9OK26.7s692 / 573
CG-AL-H029hard262.5 / 10016/18OK20.8s3.4k / 2.4k
CG-AL-H030hard20.0 / 1000/0FAIL8.9s2.4k / 1.4k
CG-AL-H031hard2100.0 / 10022/22OK19.4s3.2k / 2.2k
CG-AL-H032hard2100.0 / 10019/19OK20.8s2.8k / 2.0k
CG-AL-H033hard1100.0 / 1005/5OK2m 28s823 / 1.5k
CG-AL-H034hard2100.0 / 1003/3OK14.1s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK15.8s317 / 102
CG-AL-H036hard20.0 / 1000/0FAIL7.5s1.3k / 327
CG-AL-H037hard20.0 / 1000/0FAIL6.9s1.6k / 402
CG-AL-H038hard20.0 / 1000/0FAIL7.0s1.7k / 624
CG-AL-H039hard1100.0 / 1004/4OK15.0s524 / 273
CG-AL-H040hard1100.0 / 1002/2OK14.5s430 / 174
CG-AL-H041hard20.0 / 1000/0FAIL7.4s2.1k / 1.2k
CG-AL-H042hard20.0 / 1000/0FAIL10.4s1.1k / 301
CG-AL-H043hard1100.0 / 1005/5OK13.6s430 / 99
CG-AL-H050hard262.5 / 1002/3OK13.5s1.7k / 421
CG-AL-H051hard1100.0 / 1004/4OK15.0s695 / 199
CG-AL-H052hard1100.0 / 1005/5OK16.0s784 / 219
CG-AL-H053hard2100.0 / 1004/4OK14.0s1.5k / 533
CG-AL-H054hard2100.0 / 1005/5OK16.8s2.4k / 1.3k
CG-AL-H056hard20.0 / 1000/0FAIL6.4s1.7k / 330
CG-AL-H057hard1100.0 / 1004/4OK2m 33s776 / 392
CG-AL-H058hard1100.0 / 1005/5OK14.7s644 / 325
CG-AL-H205hard2100.0 / 1006/6OK15.1s1.9k / 1.1k
CG-AL-M001medium20.0 / 1000/0FAIL7.5s1.9k / 1.1k
CG-AL-M002medium262.5 / 10021/22OK17.8s4.0k / 2.0k
CG-AL-M003medium20.0 / 1000/0FAIL9.5s1.8k / 1.7k
CG-AL-M004medium1100.0 / 10012/12OK2m 29s496 / 1.0k
CG-AL-M005medium20.0 / 1000/0FAIL13.0s2.5k / 3.8k
CG-AL-M006medium20.0 / 1000/0FAIL10.1s2.1k / 2.3k
CG-AL-M007medium20.0 / 1000/0FAIL16.1s3.1k / 4.4k
CG-AL-M008medium262.5 / 1008/12OK1m 4s3.4k / 6.0k
CG-AL-M009medium1100.0 / 10011/11OK30.9s475 / 3.8k
CG-AL-M010medium2100.0 / 10021/21OK3m 4s2.6k / 3.9k
CG-AL-M020medium2100.0 / 10017/17OK34.0s3.2k / 1.9k
CG-AL-M021medium20.0 / 1000/0FAIL26.9s2.1k / 1.1k
CG-AL-M022medium1100.0 / 1009/9OK16.8s554 / 813
CG-AL-M023medium262.5 / 10010/11OK15.6s1.9k / 1.1k
CG-AL-M024medium2100.0 / 10010/10OK24.7s2.5k / 2.5k
CG-AL-M025medium262.5 / 1002/7OK14.1s1.4k / 780
CG-AL-M026medium1100.0 / 1008/8OK14.9s426 / 347
CG-AL-M027medium20.0 / 1000/0FAIL19.8s3.9k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK2m 35s1.2k / 610
CG-AL-M029medium2100.0 / 1003/3OK2m 30s998 / 220
CG-AL-M031medium20.0 / 1000/0FAIL8.2s2.1k / 1.7k
CG-AL-M032medium20.0 / 1000/0FAIL6.3s1.4k / 435
CG-AL-M033medium2100.0 / 1002/2OK14.6s1.3k / 537
CG-AL-M034medium262.5 / 1001/2OK14.2s1.5k / 512
CG-AL-M035medium1100.0 / 1002/2OK14.1s358 / 98
CG-AL-M036medium20.0 / 1000/0FAIL6.4s1.7k / 613
CG-AL-M037medium20.0 / 1000/0FAIL6.6s1.5k / 508
CG-AL-M038medium1100.0 / 1002/2OK13.4s433 / 186
CG-AL-M039medium1100.0 / 1002/2OK2m 17s502 / 369
CG-AL-M040medium262.5 / 1001/2OK13.7s908 / 359
CG-AL-M041medium20.0 / 1000/0FAIL5.6s846 / 238
CG-AL-M042medium2100.0 / 1008/8OK16.6s3.0k / 743
CG-AL-M043medium262.5 / 1000/5OK13.5s1.4k / 540
CG-AL-M044medium1100.0 / 1006/6OK2m 34s719 / 749
CG-AL-M045medium2100.0 / 1006/6OK13.4s2.2k / 378
CG-AL-M088medium1100.0 / 1006/6OK14.5s451 / 429
CG-AL-M112medium2100.0 / 1004/4OK15.5s2.2k / 1.5k