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.

78.2% 86/110 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.

62.7 / 100
Cost $3.16
Tokens 176k / 175k input / output, all attempts
Duration 2h 5m
Filter:
Per-task results for run faf6dac6-80c2-46e3-a3aa-bd6c6b4d59da
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK17.7s789 / 580
CG-AL-E002easy1100.0 / 1006/6OK2m 33s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK24.0s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK31.2s300 / 328
CG-AL-E005easy1100.0 / 10013/13OK34.2s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK2m 53s301 / 419
CG-AL-E007easy1100.0 / 1007/7OK44.0s371 / 164
CG-AL-E008easy1100.0 / 1006/6OK50.5s291 / 355
CG-AL-E009easy2100.0 / 1005/5OK18.0s793 / 481
CG-AL-E010easy20.0 / 1000/0FAIL13.4s761 / 277
CG-AL-E031easy1100.0 / 1003/3OK59.7s428 / 455
CG-AL-E032easy1100.0 / 1001/1OK1m 0s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK18.1s385 / 369
CG-AL-E050easy20.0 / 1000/0FAIL11.1s2.2k / 704
CG-AL-E051easy1100.0 / 10015/15OK25.4s520 / 859
CG-AL-E052easy2100.0 / 10016/16OK19.0s1.6k / 610
CG-AL-E053easy1100.0 / 1003/3OK2m 28s312 / 128
CG-AL-E054easy20.0 / 1000/0FAIL14.0s1.2k / 684
CG-AL-E055easy1100.0 / 1008/8OK18.2s385 / 215
CG-AL-E056easy2100.0 / 10015/15OK19.6s2.0k / 801
CG-AL-E057easy20.0 / 1000/0FAIL13.5s1.6k / 1.0k
CG-AL-E058easy2100.0 / 1001/1OK17.1s993 / 320
CG-AL-H001hard1100.0 / 10025/25OK25.1s491 / 335
CG-AL-H002hard1100.0 / 1004/4OK19.4s496 / 626
CG-AL-H003hard1100.0 / 1005/5OK22.4s524 / 721
CG-AL-H004hard1100.0 / 10014/14OK22.4s535 / 501
CG-AL-H005hard1100.0 / 1006/6OK22.7s802 / 674
CG-AL-H006hard1100.0 / 1006/6OK17.7s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK20.6s625 / 703
CG-AL-H008hard1100.0 / 10010/10OK25.9s588 / 416
CG-AL-H009hard1100.0 / 10011/11OK23.2s688 / 907
CG-AL-H010hard1100.0 / 1008/8OK18.5s561 / 406
CG-AL-H011hard2100.0 / 1005/5OK17.4s1.0k / 441
CG-AL-H013hard1100.0 / 1009/9OK17.4s392 / 322
CG-AL-H014hard2100.0 / 1007/7OK21.3s2.0k / 1.7k
CG-AL-H015hard1100.0 / 1004/4OK17.8s443 / 286
CG-AL-H016hard1100.0 / 1004/4OK17.0s446 / 284
CG-AL-H017hard20.0 / 1000/0FAIL11.7s1.2k / 809
CG-AL-H018hard1100.0 / 1006/6OK28.4s462 / 552
CG-AL-H019hard1100.0 / 1005/5OK17.2s349 / 168
CG-AL-H020hard2100.0 / 10010/10OK25.7s2.5k / 1.8k
CG-AL-H021hard20.0 / 1000/0FAIL22.0s18k / 2.0k
CG-AL-H022hard2100.0 / 10021/21OK1m 8s2.8k / 2.0k
CG-AL-H023hard20.0 / 1000/0FAIL2m 49s15k / 21k
CG-AL-H024hard1100.0 / 1009/9OK1m 56s573 / 813
CG-AL-H025hard1100.0 / 1007/7OK17.9s388 / 210
CG-AL-H026hard1100.0 / 1008/8OK18.7s509 / 365
CG-AL-H027hard1100.0 / 1004/4OK20.0s827 / 212
CG-AL-H028hard2100.0 / 1009/9OK29.6s4.1k / 1.6k
CG-AL-H029hard262.5 / 10015/18OK39.4s3.3k / 3.2k
CG-AL-H030hard262.5 / 1009/10OK23.7s2.3k / 1.6k
CG-AL-H031hard2100.0 / 10022/22OK23.7s3.3k / 2.4k
CG-AL-H032hard1100.0 / 10019/19OK26.5s824 / 979
CG-AL-H033hard1100.0 / 1005/5OK2m 49s823 / 1.8k
CG-AL-H034hard2100.0 / 1003/3OK16.0s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK16.3s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK17.1s419 / 139
CG-AL-H037hard2100.0 / 1003/3OK17.8s1.3k / 398
CG-AL-H038hard2100.0 / 1003/3OK22.3s1.5k / 636
CG-AL-H039hard1100.0 / 1004/4OK17.7s524 / 253
CG-AL-H040hard1100.0 / 1002/2OK17.8s430 / 176
CG-AL-H041hard2100.0 / 1003/3OK29.0s2.8k / 1.3k
CG-AL-H042hard1100.0 / 1003/3OK16.6s434 / 154
CG-AL-H043hard1100.0 / 1005/5OK16.4s430 / 98
CG-AL-H050hard262.5 / 1002/3OK19.0s1.6k / 994
CG-AL-H051hard1100.0 / 1004/4OK16.5s695 / 138
CG-AL-H052hard1100.0 / 1005/5OK16.5s784 / 119
CG-AL-H053hard1100.0 / 1004/4OK18.4s598 / 270
CG-AL-H054hard20.0 / 1000/0FAIL10.8s2.5k / 1.5k
CG-AL-H056hard20.0 / 1000/0FAIL7.5s1.7k / 367
CG-AL-H057hard1100.0 / 1004/4OK2m 37s776 / 307
CG-AL-H058hard1100.0 / 1005/5OK18.0s644 / 325
CG-AL-H205hard1100.0 / 1006/6OK22.6s535 / 476
CG-AL-M001medium2100.0 / 10010/10OK2m 36s2.2k / 1.3k
CG-AL-M002medium1100.0 / 10022/22OK23.6s471 / 522
CG-AL-M003medium1100.0 / 1009/9OK25.1s449 / 800
CG-AL-M004medium1100.0 / 10012/12OK3m 4s496 / 1.5k
CG-AL-M005medium2100.0 / 10022/22OK38.8s2.4k / 4.8k
CG-AL-M006medium262.5 / 10017/18OK35.1s2.3k / 3.8k
CG-AL-M007medium20.0 / 1000/0FAIL44.8s3.0k / 9.6k
CG-AL-M008medium20.0 / 1000/0FAIL3m 2s14k / 32k
CG-AL-M009medium20.0 / 1000/0FAIL1m 41s8.6k / 24k
CG-AL-M010medium2100.0 / 10021/21OK3m 43s2.5k / 4.3k
CG-AL-M020medium20.0 / 1000/0FAIL45.6s3.3k / 2.2k
CG-AL-M021medium1100.0 / 10011/11OK46.5s595 / 654
CG-AL-M022medium1100.0 / 1009/9OK22.6s554 / 760
CG-AL-M023medium262.5 / 10010/11OK24.5s1.9k / 1.3k
CG-AL-M024medium2100.0 / 10010/10OK22.9s2.5k / 2.3k
CG-AL-M025medium262.5 / 1002/7OK20.8s3.1k / 865
CG-AL-M026medium1100.0 / 1008/8OK19.1s426 / 384
CG-AL-M027medium2100.0 / 10018/18OK37.0s4.0k / 4.9k
CG-AL-M028medium2100.0 / 1003/3OK2m 33s1.2k / 648
CG-AL-M029medium2100.0 / 1003/3OK2m 31s1.0k / 232
CG-AL-M031medium20.0 / 1000/0FAIL18.2s3.3k / 2.1k
CG-AL-M032medium1100.0 / 1003/3OK17.5s549 / 246
CG-AL-M033medium1100.0 / 1002/2OK17.6s492 / 271
CG-AL-M034medium262.5 / 1001/2OK21.9s1.8k / 832
CG-AL-M035medium1100.0 / 1002/2OK16.5s358 / 98
CG-AL-M036medium2100.0 / 1002/2OK24.9s1.8k / 1.0k
CG-AL-M037medium20.0 / 1000/0FAIL8.8s1.5k / 570
CG-AL-M038medium1100.0 / 1002/2OK17.1s433 / 180
CG-AL-M039medium20.0 / 1000/0FAIL19.2s2.3k / 1.8k
CG-AL-M040medium20.0 / 1000/0FAIL8.6s920 / 433
CG-AL-M041medium1100.0 / 1003/3OK17.9s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK22.3s538 / 322
CG-AL-M043medium1100.0 / 1005/5OK20.4s483 / 501
CG-AL-M044medium1100.0 / 1006/6OK2m 37s719 / 641
CG-AL-M045medium1100.0 / 1006/6OK17.6s776 / 185
CG-AL-M088medium1100.0 / 1006/6OK20.0s451 / 450
CG-AL-M112medium1100.0 / 1004/4OK21.8s620 / 735