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.

82.7% 91/110 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.

67.0 / 100
Cost $4.84
Tokens 222k / 149k input / output, all attempts
Duration 1h 19m
Filter:
Per-task results for run 17a3f05f-9aa0-4f22-9bc5-619a6ab72bd3
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.6s413 / 386
CG-AL-E002easy1100.0 / 1006/6OK2m 27s428 / 424
CG-AL-E003easy1100.0 / 1005/5OK24.8s405 / 150
CG-AL-E004easy1100.0 / 1006/6OK28.9s465 / 365
CG-AL-E005easy1100.0 / 10013/13OK34.3s486 / 551
CG-AL-E006easy1100.0 / 1007/7OK2m 45s465 / 595
CG-AL-E007easy1100.0 / 1007/7OK42.2s553 / 277
CG-AL-E008easy1100.0 / 1006/6OK46.3s465 / 489
CG-AL-E009easy1100.0 / 1005/5OK50.6s437 / 237
CG-AL-E010easy1100.0 / 1005/5OK52.7s462 / 232
CG-AL-E031easy1100.0 / 1003/3OK54.4s673 / 657
CG-AL-E032easy1100.0 / 1001/1OK53.9s372 / 240
CG-AL-E045easy1100.0 / 1004/4OK18.2s560 / 430
CG-AL-E050easy1100.0 / 10013/13OK16.9s630 / 315
CG-AL-E051easy1100.0 / 10015/15OK24.0s771 / 1.2k
CG-AL-E052easy2100.0 / 10016/16OK17.5s2.4k / 759
CG-AL-E053easy1100.0 / 1003/3OK2m 35s456 / 176
CG-AL-E054easy2100.0 / 1009/9OK17.7s1.7k / 670
CG-AL-E055easy1100.0 / 1008/8OK20.6s561 / 299
CG-AL-E056easy2100.0 / 10015/15OK18.7s2.8k / 978
CG-AL-E057easy20.0 / 1000/0FAIL10.1s2.3k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK19.6s623 / 166
CG-AL-H001hard1100.0 / 10025/25OK22.1s721 / 426
CG-AL-H002hard1100.0 / 1004/4OK21.5s742 / 862
CG-AL-H003hard1100.0 / 1005/5OK21.6s761 / 832
CG-AL-H004hard1100.0 / 10014/14OK19.9s774 / 663
CG-AL-H005hard1100.0 / 1006/6OK25.2s1.2k / 873
CG-AL-H006hard1100.0 / 1006/6OK18.6s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK22.6s947 / 995
CG-AL-H008hard1100.0 / 10010/10OK19.9s881 / 584
CG-AL-H009hard1100.0 / 10011/11OK28.1s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK21.2s896 / 630
CG-AL-H011hard20.0 / 1000/0FAIL8.0s1.6k / 610
CG-AL-H013hard1100.0 / 1009/9OK18.2s602 / 455
CG-AL-H014hard2100.0 / 1007/7OK25.3s4.1k / 2.8k
CG-AL-H015hard1100.0 / 1004/4OK18.2s658 / 447
CG-AL-H016hard1100.0 / 1004/4OK18.2s698 / 435
CG-AL-H017hard20.0 / 1000/0FAIL9.3s1.7k / 818
CG-AL-H018hard1100.0 / 1006/6OK20.4s727 / 839
CG-AL-H019hard1100.0 / 1005/5OK16.2s528 / 231
CG-AL-H020hard2100.0 / 10010/10OK22.5s2.8k / 2.2k
CG-AL-H021hard2100.0 / 10020/20OK24.3s30k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK26.3s1.2k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL2m 16s21k / 22k
CG-AL-H024hard1100.0 / 1009/9OK37.9s847 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK42.4s570 / 300
CG-AL-H026hard1100.0 / 1008/8OK20.9s745 / 534
CG-AL-H027hard2100.0 / 1004/4OK17.4s3.4k / 602
CG-AL-H028hard1100.0 / 1009/9OK21.1s1.0k / 787
CG-AL-H029hard2100.0 / 10018/18OK25.6s4.3k / 3.2k
CG-AL-H030hard2100.0 / 10010/10OK22.7s3.4k / 2.2k
CG-AL-H031hard1100.0 / 10022/22OK32.1s1.6k / 1.6k
CG-AL-H032hard1100.0 / 10019/19OK45.2s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK2m 53s1.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK16.6s2.1k / 461
CG-AL-H035hard1100.0 / 1003/3OK16.8s495 / 198
CG-AL-H036hard20.0 / 1000/0FAIL7.7s1.7k / 480
CG-AL-H037hard20.0 / 1000/0FAIL8.4s2.1k / 542
CG-AL-H038hard1100.0 / 1003/3OK17.1s887 / 334
CG-AL-H039hard1100.0 / 1004/4OK19.7s773 / 382
CG-AL-H040hard1100.0 / 1002/2OK16.3s645 / 255
CG-AL-H041hard1100.0 / 1003/3OK23.1s923 / 587
CG-AL-H042hard1100.0 / 1003/3OK16.8s658 / 179
CG-AL-H043hard1100.0 / 1005/5OK16.5s650 / 168
CG-AL-H050hard20.0 / 1000/0FAIL16.7s2.5k / 800
CG-AL-H051hard1100.0 / 1004/4OK16.6s989 / 194
CG-AL-H052hard1100.0 / 1005/5OK18.2s1.1k / 155
CG-AL-H053hard1100.0 / 1004/4OK18.5s847 / 331
CG-AL-H054hard20.0 / 1000/0FAIL10.3s3.0k / 1.0k
CG-AL-H056hard20.0 / 1000/0FAIL8.6s2.4k / 449
CG-AL-H057hard1100.0 / 1004/4OK2m 28s1.1k / 487
CG-AL-H058hard1100.0 / 1005/5OK17.9s929 / 457
CG-AL-H205hard1100.0 / 1006/6OK19.1s779 / 662
CG-AL-M001medium20.0 / 1000/0FAIL14.1s2.2k / 1.4k
CG-AL-M002medium1100.0 / 10022/22OK20.5s725 / 776
CG-AL-M003medium2100.0 / 1009/9OK27.2s2.6k / 2.4k
CG-AL-M004medium1100.0 / 10012/12OK2m 50s773 / 1.8k
CG-AL-M005medium1100.0 / 10022/22OK39.9s943 / 2.9k
CG-AL-M006medium2100.0 / 10018/18OK31.9s3.8k / 3.9k
CG-AL-M007medium20.0 / 1000/0FAIL27.7s3.5k / 5.2k
CG-AL-M008medium20.0 / 1000/0FAIL2m 47s21k / 22k
CG-AL-M009medium1100.0 / 10011/11OK1m 23s746 / 3.0k
CG-AL-M010medium1100.0 / 10021/21OK4m 3s958 / 3.3k
CG-AL-M020medium2100.0 / 10017/17OK21.9s3.0k / 2.0k
CG-AL-M021medium1100.0 / 10011/11OK22.6s908 / 816
CG-AL-M022medium1100.0 / 1009/9OK26.9s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK19.9s2.7k / 1.5k
CG-AL-M024medium1100.0 / 10010/10OK28.0s757 / 1.6k
CG-AL-M025medium2100.0 / 1007/7OK19.8s4.2k / 1.0k
CG-AL-M026medium2100.0 / 1008/8OK29.3s2.3k / 1.3k
CG-AL-M027medium2100.0 / 10018/18OK31.2s5.9k / 4.4k
CG-AL-M028medium20.0 / 1000/0FAIL13.8s1.7k / 896
CG-AL-M029medium2100.0 / 1003/3OK2m 19s1.4k / 314
CG-AL-M031medium20.0 / 1000/0FAIL14.7s3.0k / 2.4k
CG-AL-M032medium2100.0 / 1003/3OK16.8s2.6k / 670
CG-AL-M033medium1100.0 / 1002/2OK18.3s735 / 381
CG-AL-M034medium262.5 / 1001/2OK20.9s2.3k / 1.2k
CG-AL-M035medium1100.0 / 1002/2OK15.8s544 / 157
CG-AL-M036medium1100.0 / 1002/2OK18.2s910 / 515
CG-AL-M037medium20.0 / 1000/0FAIL8.9s2.1k / 708
CG-AL-M038medium1100.0 / 1002/2OK17.5s638 / 266
CG-AL-M039medium20.0 / 1000/0FAIL10.9s2.1k / 1.2k
CG-AL-M040medium20.0 / 1000/0FAIL7.8s1.3k / 472
CG-AL-M041medium1100.0 / 1003/3OK18.1s501 / 157
CG-AL-M042medium2100.0 / 1008/8OK19.4s4.3k / 821
CG-AL-M043medium1100.0 / 1005/5OK20.0s677 / 410
CG-AL-M044medium1100.0 / 1006/6OK2m 52s985 / 867
CG-AL-M045medium1100.0 / 1006/6OK18.9s1.0k / 242
CG-AL-M088medium1100.0 / 1006/6OK25.0s673 / 650
CG-AL-M112medium1100.0 / 1004/4OK22.1s908 / 969