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.

91.8% 101/110 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.

78.7 / 100
Cost $12.41
Tokens 191k / 210k input / output, all attempts
Duration 1h 43m
Filter:
Per-task results for run 05dc356f-e4b9-4baf-a85f-9d48cf808fa8
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK31.0s1.3k / 870
CG-AL-E002easy1100.0 / 1006/6OK2m 35s428 / 460
CG-AL-E003easy1100.0 / 1005/5OK17.9s405 / 168
CG-AL-E004easy1100.0 / 1006/6OK22.9s465 / 374
CG-AL-E005easy1100.0 / 10013/13OK27.9s486 / 650
CG-AL-E006easy1100.0 / 1007/7OK2m 40s465 / 713
CG-AL-E007easy1100.0 / 1007/7OK33.2s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK36.8s465 / 770
CG-AL-E009easy1100.0 / 1005/5OK35.7s437 / 343
CG-AL-E010easy1100.0 / 1005/5OK35.8s462 / 311
CG-AL-E031easy1100.0 / 1003/3OK46.8s673 / 638
CG-AL-E032easy1100.0 / 1001/1OK39.9s372 / 275
CG-AL-E045easy1100.0 / 1004/4OK24.2s560 / 493
CG-AL-E050easy2100.0 / 10013/13OK37.9s3.0k / 3.0k
CG-AL-E051easy1100.0 / 10015/15OK36.5s771 / 2.2k
CG-AL-E052easy2100.0 / 10016/16OK38.4s2.4k / 896
CG-AL-E053easy1100.0 / 1003/3OK2m 56s456 / 257
CG-AL-E054easy2100.0 / 1009/9OK25.7s1.7k / 1.0k
CG-AL-E055easy1100.0 / 1008/8OK26.5s561 / 943
CG-AL-E056easy2100.0 / 10015/15OK19.9s2.8k / 1.2k
CG-AL-E057easy2100.0 / 1008/8OK27.8s2.1k / 2.2k
CG-AL-E058easy1100.0 / 1001/1OK30.7s623 / 231
CG-AL-H001hard1100.0 / 10025/25OK23.4s721 / 391
CG-AL-H002hard1100.0 / 1004/4OK22.0s742 / 784
CG-AL-H003hard1100.0 / 1005/5OK22.7s761 / 882
CG-AL-H004hard1100.0 / 10014/14OK19.4s774 / 589
CG-AL-H005hard1100.0 / 1006/6OK21.9s1.2k / 830
CG-AL-H006hard1100.0 / 1006/6OK18.0s710 / 373
CG-AL-H007hard1100.0 / 10010/10OK23.7s947 / 1.1k
CG-AL-H008hard1100.0 / 10010/10OK21.7s881 / 661
CG-AL-H009hard1100.0 / 10011/11OK24.5s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK20.2s896 / 692
CG-AL-H011hard1100.0 / 1005/5OK18.5s574 / 481
CG-AL-H013hard1100.0 / 1009/9OK25.2s602 / 936
CG-AL-H014hard2100.0 / 1007/7OK21.9s2.2k / 2.0k
CG-AL-H015hard1100.0 / 1004/4OK18.1s658 / 442
CG-AL-H016hard1100.0 / 1004/4OK24.7s698 / 631
CG-AL-H017hard1100.0 / 1003/3OK27.5s610 / 1.3k
CG-AL-H018hard1100.0 / 1006/6OK34.6s727 / 2.1k
CG-AL-H019hard1100.0 / 1005/5OK23.8s528 / 515
CG-AL-H020hard1100.0 / 10010/10OK33.5s781 / 1.5k
CG-AL-H021hard2100.0 / 10020/20OK28.7s30k / 2.6k
CG-AL-H022hard1100.0 / 10021/21OK37.4s1.2k / 2.6k
CG-AL-H023hard20.0 / 1000/0FAIL1m 50s15k / 27k
CG-AL-H024hard1100.0 / 1009/9OK24.1s847 / 1.1k
CG-AL-H025hard1100.0 / 1007/7OK21.7s570 / 322
CG-AL-H026hard1100.0 / 1008/8OK20.5s745 / 547
CG-AL-H027hard1100.0 / 1004/4OK20.8s1.1k / 495
CG-AL-H028hard1100.0 / 1009/9OK22.7s1.0k / 862
CG-AL-H029hard1100.0 / 10018/18OK34.0s1.3k / 2.1k
CG-AL-H030hard2100.0 / 10010/10OK26.1s5.0k / 5.5k
CG-AL-H031hard1100.0 / 10022/22OK35.9s1.6k / 2.3k
CG-AL-H032hard1100.0 / 10019/19OK30.1s1.3k / 1.8k
CG-AL-H033hard1100.0 / 1005/5OK3m 1s1.2k / 2.4k
CG-AL-H034hard2100.0 / 1003/3OK28.1s2.2k / 2.5k
CG-AL-H035hard1100.0 / 1003/3OK30.9s495 / 200
CG-AL-H036hard2100.0 / 1005/5OK22.7s1.6k / 2.0k
CG-AL-H037hard1100.0 / 1003/3OK21.2s805 / 342
CG-AL-H038hard1100.0 / 1003/3OK20.0s887 / 517
CG-AL-H039hard1100.0 / 1004/4OK19.7s773 / 458
CG-AL-H040hard1100.0 / 1002/2OK18.6s645 / 305
CG-AL-H041hard2100.0 / 1003/3OK25.0s3.7k / 3.3k
CG-AL-H042hard1100.0 / 1003/3OK17.4s658 / 245
CG-AL-H043hard1100.0 / 1005/5OK17.2s650 / 202
CG-AL-H050hard1100.0 / 1003/3OK28.7s813 / 1.3k
CG-AL-H051hard1100.0 / 1004/4OK20.8s989 / 454
CG-AL-H052hard1100.0 / 1005/5OK17.1s1.1k / 227
CG-AL-H053hard1100.0 / 1004/4OK17.6s847 / 337
CG-AL-H054hard2100.0 / 1005/5OK19.7s3.0k / 1.2k
CG-AL-H056hard2100.0 / 1004/4OK23.4s2.4k / 961
CG-AL-H057hard1100.0 / 1004/4OK2m 42s1.1k / 489
CG-AL-H058hard1100.0 / 1005/5OK21.6s929 / 695
CG-AL-H205hard1100.0 / 1006/6OK22.3s779 / 755
CG-AL-M001medium20.0 / 1000/0FAIL17.4s2.3k / 1.8k
CG-AL-M002medium1100.0 / 10022/22OK21.2s725 / 778
CG-AL-M003medium1100.0 / 1009/9OK28.3s687 / 1.4k
CG-AL-M004medium1100.0 / 10012/12OK3m 19s773 / 2.3k
CG-AL-M005medium1100.0 / 10022/22OK42.7s943 / 3.4k
CG-AL-M006medium2100.0 / 10018/18OK1m 39s4.4k / 5.0k
CG-AL-M007medium20.0 / 1000/0FAIL59.0s8.6k / 21k
CG-AL-M008medium20.0 / 1000/0FAIL3m 4s11k / 32k
CG-AL-M009medium20.0 / 1000/0FAIL2m 3s8.1k / 10k
CG-AL-M010medium1100.0 / 10021/21OK3m 37s958 / 3.5k
CG-AL-M020medium1100.0 / 10017/17OK1m 43s883 / 1.1k
CG-AL-M021medium1100.0 / 10011/11OK1m 40s908 / 894
CG-AL-M022medium1100.0 / 1009/9OK51.1s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK38.7s2.8k / 2.6k
CG-AL-M024medium1100.0 / 10010/10OK25.5s757 / 1.5k
CG-AL-M025medium1100.0 / 1007/7OK19.8s655 / 618
CG-AL-M026medium1100.0 / 1008/8OK23.9s624 / 1.0k
CG-AL-M027medium1100.0 / 10018/18OK30.5s1.4k / 2.0k
CG-AL-M028medium2100.0 / 1003/3OK2m 26s1.7k / 1.1k
CG-AL-M029medium2100.0 / 1003/3OK2m 29s1.4k / 456
CG-AL-M031medium20.0 / 1000/0FAIL18.2s2.9k / 2.3k
CG-AL-M032medium1100.0 / 1003/3OK17.2s793 / 339
CG-AL-M033medium1100.0 / 1002/2OK17.6s735 / 385
CG-AL-M034medium262.5 / 1001/2OK27.4s2.6k / 1.9k
CG-AL-M035medium1100.0 / 1002/2OK16.3s544 / 189
CG-AL-M036medium1100.0 / 1002/2OK19.7s910 / 601
CG-AL-M037medium2100.0 / 1002/2OK37.7s2.1k / 2.3k
CG-AL-M038medium1100.0 / 1002/2OK17.9s638 / 318
CG-AL-M039medium1100.0 / 1002/2OK2m 29s710 / 653
CG-AL-M040medium262.5 / 1001/2OK23.9s1.3k / 1.1k
CG-AL-M041medium1100.0 / 1003/3OK15.9s501 / 157
CG-AL-M042medium1100.0 / 1008/8OK18.3s753 / 431
CG-AL-M043medium1100.0 / 1005/5OK22.5s677 / 780
CG-AL-M044medium1100.0 / 1006/6OK2m 52s985 / 898
CG-AL-M045medium1100.0 / 1006/6OK19.6s1.0k / 390
CG-AL-M088medium1100.0 / 1006/6OK20.2s673 / 663
CG-AL-M112medium1100.0 / 1004/4OK22.0s908 / 981