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.

80.9% 89/110 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.

64.3 / 100
Cost $3.07
Tokens 169k / 171k input / output, all attempts
Duration 1h 45m
Filter:
Per-task results for run 203a1b90-d0ce-4245-b316-a52365774a11
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK18.9s272 / 272
CG-AL-E002easy1100.0 / 1006/6OK2m 35s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK24.7s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK30.6s300 / 328
CG-AL-E005easy1100.0 / 10013/13OK35.4s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK2m 55s301 / 420
CG-AL-E007easy1100.0 / 1007/7OK46.7s371 / 154
CG-AL-E008easy1100.0 / 1006/6OK50.3s291 / 355
CG-AL-E009easy1100.0 / 1005/5OK55.1s285 / 250
CG-AL-E010easy20.0 / 1000/0FAIL13.7s763 / 268
CG-AL-E031easy1100.0 / 1003/3OK1m 0s428 / 455
CG-AL-E032easy1100.0 / 1001/1OK57.9s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK17.8s385 / 369
CG-AL-E050easy2100.0 / 10013/13OK25.7s2.0k / 1.1k
CG-AL-E051easy1100.0 / 10015/15OK24.3s520 / 856
CG-AL-E052easy2100.0 / 10016/16OK19.5s1.6k / 674
CG-AL-E053easy1100.0 / 1003/3OK2m 31s312 / 128
CG-AL-E054easy2100.0 / 1009/9OK23.8s1.2k / 773
CG-AL-E055easy1100.0 / 1008/8OK17.8s385 / 215
CG-AL-E056easy2100.0 / 10015/15OK18.9s2.0k / 799
CG-AL-E057easy20.0 / 1000/0FAIL12.9s1.6k / 1.1k
CG-AL-E058easy2100.0 / 1001/1OK17.5s991 / 333
CG-AL-H001hard1100.0 / 10025/25OK18.7s491 / 335
CG-AL-H002hard1100.0 / 1004/4OK19.8s496 / 626
CG-AL-H003hard1100.0 / 1005/5OK24.0s524 / 721
CG-AL-H004hard1100.0 / 10014/14OK20.4s535 / 495
CG-AL-H005hard1100.0 / 1006/6OK22.0s802 / 675
CG-AL-H006hard1100.0 / 1006/6OK18.0s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK21.9s625 / 688
CG-AL-H008hard1100.0 / 10010/10OK20.2s588 / 416
CG-AL-H009hard1100.0 / 10011/11OK24.3s688 / 907
CG-AL-H010hard1100.0 / 1008/8OK19.7s561 / 406
CG-AL-H011hard2100.0 / 1005/5OK18.7s1.0k / 483
CG-AL-H013hard1100.0 / 1009/9OK17.4s392 / 322
CG-AL-H014hard2100.0 / 1007/7OK26.8s1.9k / 1.7k
CG-AL-H015hard1100.0 / 1004/4OK17.3s443 / 286
CG-AL-H016hard1100.0 / 1004/4OK24.6s446 / 264
CG-AL-H017hard20.0 / 1000/0FAIL10.3s1.2k / 739
CG-AL-H018hard1100.0 / 1006/6OK19.6s462 / 552
CG-AL-H019hard1100.0 / 1005/5OK16.2s349 / 168
CG-AL-H020hard20.0 / 1000/0FAIL14.1s2.5k / 2.0k
CG-AL-H021hard2100.0 / 10020/20OK26.2s19k / 1.8k
CG-AL-H022hard2100.0 / 10021/21OK26.9s2.8k / 2.0k
CG-AL-H023hard20.0 / 1000/0FAIL3m 3s15k / 23k
CG-AL-H024hard1100.0 / 1009/9OK22.7s573 / 780
CG-AL-H025hard1100.0 / 1007/7OK1m 24s388 / 210
CG-AL-H026hard1100.0 / 1008/8OK1m 13s509 / 365
CG-AL-H027hard1100.0 / 1004/4OK18.2s827 / 212
CG-AL-H028hard2100.0 / 1009/9OK19.8s2.4k / 1.4k
CG-AL-H029hard20.0 / 1000/0FAIL15.2s3.1k / 2.5k
CG-AL-H030hard2100.0 / 10010/10OK28.3s2.3k / 1.7k
CG-AL-H031hard2100.0 / 10022/22OK28.2s3.4k / 2.5k
CG-AL-H032hard1100.0 / 10019/19OK27.5s824 / 1.2k
CG-AL-H033hard1100.0 / 1005/5OK2m 43s823 / 1.8k
CG-AL-H034hard2100.0 / 1003/3OK16.4s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK17.0s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK16.6s419 / 154
CG-AL-H037hard2100.0 / 1003/3OK22.4s1.3k / 398
CG-AL-H038hard2100.0 / 1003/3OK21.6s1.5k / 751
CG-AL-H039hard1100.0 / 1004/4OK18.5s524 / 253
CG-AL-H040hard1100.0 / 1002/2OK20.6s430 / 180
CG-AL-H041hard2100.0 / 1003/3OK28.5s2.8k / 1.3k
CG-AL-H042hard1100.0 / 1003/3OK16.8s434 / 154
CG-AL-H043hard1100.0 / 1005/5OK16.7s430 / 98
CG-AL-H050hard262.5 / 1002/3OK26.2s1.7k / 1.3k
CG-AL-H051hard1100.0 / 1004/4OK16.8s695 / 138
CG-AL-H052hard1100.0 / 1005/5OK15.8s784 / 119
CG-AL-H053hard1100.0 / 1004/4OK18.1s598 / 270
CG-AL-H054hard20.0 / 1000/0FAIL13.2s2.5k / 1.5k
CG-AL-H056hard20.0 / 1000/0FAIL8.1s1.7k / 369
CG-AL-H057hard1100.0 / 1004/4OK2m 31s776 / 307
CG-AL-H058hard1100.0 / 1005/5OK20.1s644 / 325
CG-AL-H205hard1100.0 / 1006/6OK19.5s535 / 476
CG-AL-M001medium20.0 / 1000/0FAIL12.1s2.2k / 1.4k
CG-AL-M002medium1100.0 / 10022/22OK19.5s471 / 522
CG-AL-M003medium1100.0 / 1009/9OK24.3s449 / 731
CG-AL-M004medium1100.0 / 10012/12OK2m 50s496 / 1.5k
CG-AL-M005medium2100.0 / 10022/22OK49.3s2.3k / 4.3k
CG-AL-M006medium262.5 / 10017/18OK30.2s2.3k / 4.4k
CG-AL-M007medium20.0 / 1000/0FAIL2m 10s3.2k / 9.3k
CG-AL-M008medium20.0 / 1000/0FAIL3m 3s15k / 32k
CG-AL-M009medium2100.0 / 10011/11OK42.2s5.4k / 19k
CG-AL-M010medium2100.0 / 10021/21OK2m 47s2.5k / 4.3k
CG-AL-M020medium2100.0 / 10017/17OK31.0s2.4k / 2.2k
CG-AL-M021medium2100.0 / 10011/11OK19.3s1.9k / 1.1k
CG-AL-M022medium1100.0 / 1009/9OK22.1s554 / 733
CG-AL-M023medium262.5 / 10010/11OK25.5s1.9k / 1.4k
CG-AL-M024medium1100.0 / 10010/10OK26.3s518 / 1.1k
CG-AL-M025medium262.5 / 1002/7OK22.7s3.1k / 875
CG-AL-M026medium262.5 / 1006/8OK19.2s1.2k / 859
CG-AL-M027medium2100.0 / 10018/18OK36.5s4.0k / 4.7k
CG-AL-M028medium2100.0 / 1003/3OK2m 31s1.2k / 648
CG-AL-M029medium2100.0 / 1003/3OK2m 27s1.0k / 232
CG-AL-M031medium20.0 / 1000/0FAIL18.5s3.3k / 2.1k
CG-AL-M032medium1100.0 / 1003/3OK17.6s549 / 244
CG-AL-M033medium1100.0 / 1002/2OK17.1s492 / 271
CG-AL-M034medium262.5 / 1001/2OK21.9s1.8k / 857
CG-AL-M035medium1100.0 / 1002/2OK16.4s358 / 98
CG-AL-M036medium2100.0 / 1002/2OK18.0s1.8k / 726
CG-AL-M037medium20.0 / 1000/0FAIL9.3s1.5k / 565
CG-AL-M038medium1100.0 / 1002/2OK16.1s433 / 180
CG-AL-M039medium20.0 / 1000/0FAIL15.0s2.2k / 1.5k
CG-AL-M040medium20.0 / 1000/0FAIL8.3s906 / 408
CG-AL-M041medium1100.0 / 1003/3OK15.8s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK18.1s538 / 322
CG-AL-M043medium1100.0 / 1005/5OK19.5s483 / 525
CG-AL-M044medium1100.0 / 1006/6OK2m 31s719 / 656
CG-AL-M045medium1100.0 / 1006/6OK16.5s776 / 185
CG-AL-M088medium1100.0 / 1006/6OK20.8s451 / 450
CG-AL-M112medium1100.0 / 1004/4OK22.2s620 / 807