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.

65.2 / 100
Cost $2.78
Tokens 162k / 153k input / output, all attempts
Duration 1h 32m
Filter:
Per-task results for run 6a052f35-56aa-48f8-bcde-a5227e391df2
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK18.1s272 / 272
CG-AL-E002easy1100.0 / 1006/6OK2m 26s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK21.3s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK28.9s300 / 328
CG-AL-E005easy1100.0 / 10013/13OK33.4s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK2m 55s301 / 419
CG-AL-E007easy1100.0 / 1007/7OK41.1s371 / 154
CG-AL-E008easy1100.0 / 1006/6OK45.6s291 / 355
CG-AL-E009easy1100.0 / 1005/5OK46.9s285 / 250
CG-AL-E010easy20.0 / 1000/0FAIL11.9s762 / 277
CG-AL-E031easy1100.0 / 1003/3OK50.9s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK49.0s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK18.6s385 / 369
CG-AL-E050easy20.0 / 1000/0FAIL13.8s1.9k / 727
CG-AL-E051easy1100.0 / 10015/15OK22.1s520 / 751
CG-AL-E052easy2100.0 / 10016/16OK20.4s1.6k / 610
CG-AL-E053easy1100.0 / 1003/3OK2m 34s312 / 128
CG-AL-E054easy2100.0 / 1009/9OK23.5s1.2k / 792
CG-AL-E055easy1100.0 / 1008/8OK20.6s385 / 215
CG-AL-E056easy2100.0 / 10015/15OK19.0s2.0k / 806
CG-AL-E057easy20.0 / 1000/0FAIL11.4s1.6k / 941
CG-AL-E058easy2100.0 / 1001/1OK17.5s990 / 381
CG-AL-H001hard1100.0 / 10025/25OK20.8s491 / 335
CG-AL-H002hard1100.0 / 1004/4OK20.0s496 / 626
CG-AL-H003hard1100.0 / 1005/5OK21.4s524 / 721
CG-AL-H004hard1100.0 / 10014/14OK19.4s535 / 495
CG-AL-H005hard1100.0 / 1006/6OK21.4s802 / 685
CG-AL-H006hard1100.0 / 1006/6OK16.4s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK21.1s625 / 703
CG-AL-H008hard1100.0 / 10010/10OK17.9s588 / 416
CG-AL-H009hard1100.0 / 10011/11OK24.0s688 / 821
CG-AL-H010hard1100.0 / 1008/8OK20.0s561 / 406
CG-AL-H011hard2100.0 / 1005/5OK16.2s1.0k / 437
CG-AL-H013hard1100.0 / 1009/9OK17.2s392 / 322
CG-AL-H014hard2100.0 / 1007/7OK25.2s2.9k / 1.7k
CG-AL-H015hard1100.0 / 1004/4OK16.3s443 / 286
CG-AL-H016hard1100.0 / 1004/4OK17.4s446 / 264
CG-AL-H017hard20.0 / 1000/0FAIL10.6s1.2k / 739
CG-AL-H018hard1100.0 / 1006/6OK19.4s462 / 555
CG-AL-H019hard1100.0 / 1005/5OK15.8s349 / 168
CG-AL-H020hard2100.0 / 10010/10OK21.8s2.5k / 1.8k
CG-AL-H021hard2100.0 / 10020/20OK34.2s19k / 2.1k
CG-AL-H022hard2100.0 / 10021/21OK26.9s2.8k / 2.1k
CG-AL-H023hard20.0 / 1000/0FAIL3m 17s14k / 22k
CG-AL-H024hard1100.0 / 1009/9OK28.4s573 / 794
CG-AL-H025hard1100.0 / 1007/7OK38.7s388 / 210
CG-AL-H026hard1100.0 / 1008/8OK18.4s509 / 365
CG-AL-H027hard1100.0 / 1004/4OK17.7s827 / 212
CG-AL-H028hard2100.0 / 1009/9OK24.3s4.0k / 1.5k
CG-AL-H029hard2100.0 / 10018/18OK34.0s3.1k / 2.9k
CG-AL-H030hard2100.0 / 10010/10OK22.9s2.3k / 1.6k
CG-AL-H031hard2100.0 / 10022/22OK27.8s3.4k / 2.5k
CG-AL-H032hard1100.0 / 10019/19OK38.8s824 / 1.0k
CG-AL-H033hard1100.0 / 1005/5OK2m 54s823 / 1.8k
CG-AL-H034hard2100.0 / 1003/3OK15.2s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK15.6s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK15.9s419 / 139
CG-AL-H037hard2100.0 / 1003/3OK17.2s1.3k / 400
CG-AL-H038hard2100.0 / 1003/3OK21.9s1.5k / 781
CG-AL-H039hard1100.0 / 1004/4OK17.6s524 / 253
CG-AL-H040hard1100.0 / 1002/2OK19.8s430 / 180
CG-AL-H041hard2100.0 / 1003/3OK28.2s2.8k / 1.2k
CG-AL-H042hard1100.0 / 1003/3OK17.3s434 / 154
CG-AL-H043hard1100.0 / 1005/5OK16.5s430 / 98
CG-AL-H050hard1100.0 / 1003/3OK23.7s557 / 574
CG-AL-H051hard1100.0 / 1004/4OK16.7s695 / 138
CG-AL-H052hard1100.0 / 1005/5OK18.2s784 / 119
CG-AL-H053hard1100.0 / 1004/4OK18.4s598 / 255
CG-AL-H054hard20.0 / 1000/0FAIL11.6s2.4k / 1.3k
CG-AL-H056hard20.0 / 1000/0FAIL7.8s1.7k / 367
CG-AL-H057hard1100.0 / 1004/4OK2m 28s776 / 307
CG-AL-H058hard1100.0 / 1005/5OK17.1s644 / 325
CG-AL-H205hard1100.0 / 1006/6OK20.2s535 / 476
CG-AL-M001medium2100.0 / 10010/10OK2m 45s2.1k / 1.3k
CG-AL-M002medium1100.0 / 10022/22OK22.2s471 / 522
CG-AL-M003medium1100.0 / 1009/9OK24.4s449 / 800
CG-AL-M004medium1100.0 / 10012/12OK3m 24s496 / 1.5k
CG-AL-M005medium262.5 / 10014/22OK37.3s2.3k / 4.5k
CG-AL-M006medium262.5 / 10017/18OK35.3s2.3k / 3.9k
CG-AL-M007medium20.0 / 1000/0FAIL45.8s3.1k / 9.6k
CG-AL-M008medium20.0 / 1000/0FAIL2m 58s10k / 23k
CG-AL-M009medium2100.0 / 10011/11OK55.7s3.1k / 12k
CG-AL-M010medium2100.0 / 10021/21OK3m 9s2.5k / 4.4k
CG-AL-M020medium2100.0 / 10017/17OK22.8s2.3k / 2.0k
CG-AL-M021medium2100.0 / 10011/11OK21.4s1.9k / 1.1k
CG-AL-M022medium1100.0 / 1009/9OK23.3s554 / 733
CG-AL-M023medium262.5 / 10010/11OK22.9s1.9k / 1.3k
CG-AL-M024medium1100.0 / 10010/10OK25.2s518 / 1.2k
CG-AL-M025medium262.5 / 1002/7OK22.0s3.1k / 923
CG-AL-M026medium1100.0 / 1008/8OK18.5s426 / 384
CG-AL-M027medium2100.0 / 10018/18OK35.2s4.0k / 4.7k
CG-AL-M028medium2100.0 / 1003/3OK2m 38s1.2k / 648
CG-AL-M029medium2100.0 / 1003/3OK2m 37s1.0k / 232
CG-AL-M031medium20.0 / 1000/0FAIL20.9s3.2k / 2.2k
CG-AL-M032medium1100.0 / 1003/3OK16.9s549 / 243
CG-AL-M033medium1100.0 / 1002/2OK17.7s492 / 271
CG-AL-M034medium262.5 / 1001/2OK23.2s1.8k / 863
CG-AL-M035medium1100.0 / 1002/2OK15.1s358 / 98
CG-AL-M036medium20.0 / 1000/0FAIL14.4s1.7k / 869
CG-AL-M037medium20.0 / 1000/0FAIL13.3s1.5k / 736
CG-AL-M038medium1100.0 / 1002/2OK15.8s433 / 180
CG-AL-M039medium20.0 / 1000/0FAIL20.0s2.3k / 1.8k
CG-AL-M040medium20.0 / 1000/0FAIL8.1s915 / 398
CG-AL-M041medium1100.0 / 1003/3OK16.5s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK18.2s538 / 331
CG-AL-M043medium1100.0 / 1005/5OK21.1s483 / 511
CG-AL-M044medium1100.0 / 1006/6OK2m 50s719 / 656
CG-AL-M045medium1100.0 / 1006/6OK17.4s776 / 185
CG-AL-M088medium1100.0 / 1006/6OK24.0s451 / 450
CG-AL-M112medium1100.0 / 1004/4OK21.5s620 / 735