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.

80.0% 88/110 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.

62.8 / 100
Cost $3.22
Tokens 174k / 180k input / output, all attempts
Duration 1h 39m
Filter:
Per-task results for run 3ec0deb9-c3de-44bb-8f49-9b4bed44943c
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.0s272 / 272
CG-AL-E002easy1100.0 / 1006/6OK2m 25s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK21.9s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK28.0s300 / 328
CG-AL-E005easy1100.0 / 10013/13OK32.7s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK2m 40s301 / 419
CG-AL-E007easy1100.0 / 1007/7OK41.4s371 / 164
CG-AL-E008easy1100.0 / 1006/6OK47.0s291 / 354
CG-AL-E009easy1100.0 / 1005/5OK48.9s285 / 250
CG-AL-E010easy20.0 / 1000/0FAIL8.8s764 / 266
CG-AL-E031easy1100.0 / 1003/3OK51.9s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK50.3s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK18.1s385 / 369
CG-AL-E050easy2100.0 / 10013/13OK24.7s1.9k / 971
CG-AL-E051easy1100.0 / 10015/15OK23.2s520 / 751
CG-AL-E052easy2100.0 / 10016/16OK18.4s1.6k / 642
CG-AL-E053easy1100.0 / 1003/3OK2m 21s312 / 128
CG-AL-E054easy20.0 / 1000/0FAIL11.7s1.2k / 620
CG-AL-E055easy1100.0 / 1008/8OK16.0s385 / 215
CG-AL-E056easy2100.0 / 10015/15OK18.4s2.0k / 808
CG-AL-E057easy20.0 / 1000/0FAIL16.2s1.6k / 1.1k
CG-AL-E058easy2100.0 / 1001/1OK15.9s991 / 293
CG-AL-H001hard1100.0 / 10025/25OK17.2s491 / 335
CG-AL-H002hard1100.0 / 1004/4OK19.6s496 / 626
CG-AL-H003hard1100.0 / 1005/5OK23.6s524 / 721
CG-AL-H004hard1100.0 / 10014/14OK19.7s535 / 501
CG-AL-H005hard1100.0 / 1006/6OK21.2s802 / 678
CG-AL-H006hard1100.0 / 1006/6OK17.4s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK20.6s625 / 703
CG-AL-H008hard1100.0 / 10010/10OK19.2s588 / 416
CG-AL-H009hard1100.0 / 10011/11OK23.9s688 / 849
CG-AL-H010hard1100.0 / 1008/8OK18.5s561 / 406
CG-AL-H011hard2100.0 / 1005/5OK16.9s1.0k / 486
CG-AL-H013hard1100.0 / 1009/9OK17.2s392 / 322
CG-AL-H014hard2100.0 / 1007/7OK22.6s1.9k / 1.7k
CG-AL-H015hard1100.0 / 1004/4OK16.3s443 / 286
CG-AL-H016hard1100.0 / 1004/4OK16.7s446 / 264
CG-AL-H017hard20.0 / 1000/0FAIL10.6s1.2k / 745
CG-AL-H018hard1100.0 / 1006/6OK19.4s462 / 555
CG-AL-H019hard1100.0 / 1005/5OK16.5s349 / 168
CG-AL-H020hard2100.0 / 10010/10OK21.3s2.5k / 1.7k
CG-AL-H021hard20.0 / 1000/0FAIL25.1s18k / 2.0k
CG-AL-H022hard2100.0 / 10021/21OK24.5s2.8k / 2.1k
CG-AL-H023hard20.0 / 1000/0FAIL3m 4s20k / 25k
CG-AL-H024hard1100.0 / 1009/9OK39.4s573 / 780
CG-AL-H025hard1100.0 / 1007/7OK17.8s388 / 210
CG-AL-H026hard1100.0 / 1008/8OK19.9s509 / 348
CG-AL-H027hard1100.0 / 1004/4OK26.9s827 / 212
CG-AL-H028hard2100.0 / 1009/9OK23.9s2.4k / 1.6k
CG-AL-H029hard20.0 / 1000/0FAIL21.8s3.1k / 2.5k
CG-AL-H030hard2100.0 / 10010/10OK23.1s2.3k / 1.5k
CG-AL-H031hard2100.0 / 10022/22OK28.5s3.4k / 2.7k
CG-AL-H032hard1100.0 / 10019/19OK27.1s824 / 1.2k
CG-AL-H033hard1100.0 / 1005/5OK2m 32s823 / 1.8k
CG-AL-H034hard2100.0 / 1003/3OK15.2s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK15.2s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK15.7s419 / 139
CG-AL-H037hard2100.0 / 1003/3OK15.9s1.3k / 398
CG-AL-H038hard2100.0 / 1003/3OK24.0s1.5k / 793
CG-AL-H039hard1100.0 / 1004/4OK18.4s524 / 253
CG-AL-H040hard1100.0 / 1002/2OK16.1s430 / 180
CG-AL-H041hard2100.0 / 1003/3OK20.4s2.7k / 1.1k
CG-AL-H042hard1100.0 / 1003/3OK20.8s434 / 154
CG-AL-H043hard1100.0 / 1005/5OK14.6s430 / 98
CG-AL-H050hard262.5 / 1002/3OK25.7s1.7k / 1.3k
CG-AL-H051hard1100.0 / 1004/4OK16.3s695 / 138
CG-AL-H052hard1100.0 / 1005/5OK15.5s784 / 119
CG-AL-H053hard1100.0 / 1004/4OK16.5s598 / 255
CG-AL-H054hard20.0 / 1000/0FAIL14.3s2.5k / 1.5k
CG-AL-H056hard20.0 / 1000/0FAIL8.0s1.7k / 362
CG-AL-H057hard1100.0 / 1004/4OK2m 26s776 / 307
CG-AL-H058hard1100.0 / 1005/5OK17.4s644 / 325
CG-AL-H205hard1100.0 / 1006/6OK18.9s535 / 476
CG-AL-M001medium20.0 / 1000/0FAIL11.8s2.0k / 1.2k
CG-AL-M002medium1100.0 / 10022/22OK20.0s471 / 561
CG-AL-M003medium1100.0 / 1009/9OK22.7s449 / 723
CG-AL-M004medium1100.0 / 10012/12OK2m 41s496 / 1.5k
CG-AL-M005medium20.0 / 1000/0FAIL31.0s2.3k / 5.1k
CG-AL-M006medium1100.0 / 10018/18OK41.7s445 / 2.3k
CG-AL-M007medium20.0 / 1000/0FAIL1m 2s5.3k / 17k
CG-AL-M008medium20.0 / 1000/0FAIL4m 20s15k / 32k
CG-AL-M009medium2100.0 / 10011/11OK1m 16s5.0k / 20k
CG-AL-M010medium2100.0 / 10021/21OK3m 32s2.5k / 4.4k
CG-AL-M020medium20.0 / 1000/0FAIL55.5s3.2k / 2.0k
CG-AL-M021medium2100.0 / 10011/11OK1m 5s1.9k / 1.1k
CG-AL-M022medium1100.0 / 1009/9OK22.6s554 / 733
CG-AL-M023medium262.5 / 10010/11OK24.8s1.9k / 1.3k
CG-AL-M024medium1100.0 / 10010/10OK47.1s518 / 1.1k
CG-AL-M025medium262.5 / 1002/7OK20.5s3.1k / 875
CG-AL-M026medium1100.0 / 1008/8OK17.8s426 / 384
CG-AL-M027medium2100.0 / 10018/18OK35.0s4.0k / 4.8k
CG-AL-M028medium2100.0 / 1003/3OK2m 23s1.2k / 648
CG-AL-M029medium2100.0 / 1003/3OK2m 19s1.0k / 232
CG-AL-M031medium20.0 / 1000/0FAIL21.5s3.3k / 2.1k
CG-AL-M032medium1100.0 / 1003/3OK17.2s549 / 243
CG-AL-M033medium1100.0 / 1002/2OK17.4s492 / 271
CG-AL-M034medium262.5 / 1001/2OK24.5s1.8k / 907
CG-AL-M035medium1100.0 / 1002/2OK15.1s358 / 98
CG-AL-M036medium2100.0 / 1002/2OK20.8s1.8k / 860
CG-AL-M037medium20.0 / 1000/0FAIL9.1s1.5k / 566
CG-AL-M038medium1100.0 / 1002/2OK15.7s433 / 180
CG-AL-M039medium20.0 / 1000/0FAIL21.0s2.3k / 1.8k
CG-AL-M040medium20.0 / 1000/0FAIL8.6s902 / 408
CG-AL-M041medium1100.0 / 1003/3OK17.2s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK17.2s538 / 331
CG-AL-M043medium1100.0 / 1005/5OK19.3s483 / 501
CG-AL-M044medium1100.0 / 1006/6OK2m 24s719 / 656
CG-AL-M045medium1100.0 / 1006/6OK16.0s776 / 185
CG-AL-M088medium1100.0 / 1006/6OK19.7s451 / 450
CG-AL-M112medium1100.0 / 1004/4OK24.0s620 / 735