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 $3.38
Tokens 179k / 189k input / output, all attempts
Duration 1h 38m
Filter:
Per-task results for run 9e7838df-bf03-48e4-b68e-4124d9649e65
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK34.6s272 / 272
CG-AL-E002easy1100.0 / 1006/6OK3m 10s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK39.8s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK45.9s300 / 328
CG-AL-E005easy1100.0 / 10013/13OK42.3s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK3m 43s301 / 419
CG-AL-E007easy1100.0 / 1007/7OK54.0s371 / 164
CG-AL-E008easy1100.0 / 1006/6OK57.5s291 / 355
CG-AL-E009easy1100.0 / 1005/5OK59.9s285 / 250
CG-AL-E010easy20.0 / 1000/0FAIL10.3s761 / 268
CG-AL-E031easy1100.0 / 1003/3OK1m 5s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK1m 2s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK21.9s385 / 369
CG-AL-E050easy20.0 / 1000/0FAIL15.0s1.9k / 856
CG-AL-E051easy1100.0 / 10015/15OK29.1s520 / 751
CG-AL-E052easy2100.0 / 10016/16OK23.1s1.6k / 696
CG-AL-E053easy1100.0 / 1003/3OK3m 14s312 / 128
CG-AL-E054easy20.0 / 1000/0FAIL12.6s1.2k / 711
CG-AL-E055easy1100.0 / 1008/8OK21.1s385 / 215
CG-AL-E056easy2100.0 / 10015/15OK24.3s2.0k / 805
CG-AL-E057easy20.0 / 1000/0FAIL10.1s1.5k / 816
CG-AL-E058easy20.0 / 1000/0FAIL15.9s991 / 603
CG-AL-H001hard1100.0 / 10025/25OK23.4s491 / 335
CG-AL-H002hard1100.0 / 1004/4OK24.6s496 / 626
CG-AL-H003hard1100.0 / 1005/5OK26.1s524 / 721
CG-AL-H004hard1100.0 / 10014/14OK24.6s535 / 495
CG-AL-H005hard1100.0 / 1006/6OK26.3s802 / 690
CG-AL-H006hard1100.0 / 1006/6OK22.1s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK26.2s625 / 703
CG-AL-H008hard1100.0 / 10010/10OK21.6s588 / 416
CG-AL-H009hard1100.0 / 10011/11OK27.6s688 / 849
CG-AL-H010hard1100.0 / 1008/8OK21.4s561 / 406
CG-AL-H011hard2100.0 / 1005/5OK21.6s1.0k / 442
CG-AL-H013hard1100.0 / 1009/9OK21.5s392 / 322
CG-AL-H014hard2100.0 / 1007/7OK26.4s1.9k / 1.7k
CG-AL-H015hard1100.0 / 1004/4OK18.7s443 / 286
CG-AL-H016hard1100.0 / 1004/4OK20.5s446 / 264
CG-AL-H017hard20.0 / 1000/0FAIL10.9s1.2k / 739
CG-AL-H018hard1100.0 / 1006/6OK25.0s462 / 580
CG-AL-H019hard1100.0 / 1005/5OK18.9s349 / 168
CG-AL-H020hard2100.0 / 10010/10OK28.9s2.5k / 1.8k
CG-AL-H021hard2100.0 / 10020/20OK30.1s19k / 1.9k
CG-AL-H022hard2100.0 / 10021/21OK25.0s2.7k / 2.0k
CG-AL-H023hard20.0 / 1000/0FAIL2m 39s16k / 26k
CG-AL-H024hard1100.0 / 1009/9OK43.9s573 / 780
CG-AL-H025hard1100.0 / 1007/7OK18.2s388 / 210
CG-AL-H026hard1100.0 / 1008/8OK19.6s509 / 365
CG-AL-H027hard1100.0 / 1004/4OK19.5s827 / 212
CG-AL-H028hard2100.0 / 1009/9OK25.0s3.4k / 1.5k
CG-AL-H029hard262.5 / 10015/18OK36.8s3.2k / 2.9k
CG-AL-H030hard2100.0 / 10010/10OK26.2s2.3k / 1.6k
CG-AL-H031hard2100.0 / 10022/22OK26.2s3.4k / 2.7k
CG-AL-H032hard1100.0 / 10019/19OK28.1s824 / 1.2k
CG-AL-H033hard1100.0 / 1005/5OK2m 52s823 / 1.8k
CG-AL-H034hard2100.0 / 1003/3OK16.5s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK16.3s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK16.5s419 / 139
CG-AL-H037hard2100.0 / 1003/3OK17.1s1.3k / 400
CG-AL-H038hard2100.0 / 1003/3OK21.9s1.5k / 787
CG-AL-H039hard1100.0 / 1004/4OK19.1s524 / 253
CG-AL-H040hard1100.0 / 1002/2OK17.5s430 / 180
CG-AL-H041hard2100.0 / 1003/3OK21.7s2.8k / 1.1k
CG-AL-H042hard1100.0 / 1003/3OK16.1s434 / 154
CG-AL-H043hard1100.0 / 1005/5OK16.0s430 / 98
CG-AL-H050hard2100.0 / 1003/3OK29.8s1.7k / 1.4k
CG-AL-H051hard1100.0 / 1004/4OK16.8s695 / 138
CG-AL-H052hard1100.0 / 1005/5OK16.6s784 / 119
CG-AL-H053hard1100.0 / 1004/4OK18.0s598 / 270
CG-AL-H054hard20.0 / 1000/0FAIL15.1s2.5k / 1.6k
CG-AL-H056hard20.0 / 1000/0FAIL7.1s1.7k / 357
CG-AL-H057hard1100.0 / 1004/4OK2m 33s776 / 307
CG-AL-H058hard1100.0 / 1005/5OK19.0s644 / 325
CG-AL-H205hard1100.0 / 1006/6OK19.3s535 / 476
CG-AL-M001medium20.0 / 1000/0FAIL13.1s1.9k / 1.3k
CG-AL-M002medium1100.0 / 10022/22OK21.0s471 / 610
CG-AL-M003medium1100.0 / 1009/9OK24.1s449 / 746
CG-AL-M004medium1100.0 / 10012/12OK2m 56s496 / 1.5k
CG-AL-M005medium1100.0 / 10022/22OK39.1s608 / 2.2k
CG-AL-M006medium262.5 / 10017/18OK29.7s2.3k / 3.9k
CG-AL-M007medium20.0 / 1000/0FAIL3m 42s13k / 27k
CG-AL-M008medium20.0 / 1000/0FAIL2m 52s15k / 32k
CG-AL-M009medium2100.0 / 10011/11OK46.6s5.4k / 19k
CG-AL-M010medium2100.0 / 10021/21OK2m 53s2.5k / 4.3k
CG-AL-M020medium2100.0 / 10017/17OK24.7s2.3k / 2.0k
CG-AL-M021medium1100.0 / 10011/11OK22.0s595 / 653
CG-AL-M022medium1100.0 / 1009/9OK22.8s554 / 733
CG-AL-M023medium262.5 / 10010/11OK22.5s1.9k / 1.2k
CG-AL-M024medium1100.0 / 10010/10OK23.0s518 / 1.1k
CG-AL-M025medium262.5 / 1002/7OK21.0s3.1k / 869
CG-AL-M026medium1100.0 / 1008/8OK18.9s426 / 384
CG-AL-M027medium2100.0 / 10018/18OK38.2s4.0k / 4.8k
CG-AL-M028medium2100.0 / 1003/3OK2m 34s1.2k / 626
CG-AL-M029medium2100.0 / 1003/3OK2m 30s1.0k / 232
CG-AL-M031medium20.0 / 1000/0FAIL18.3s3.2k / 2.0k
CG-AL-M032medium1100.0 / 1003/3OK17.3s549 / 243
CG-AL-M033medium1100.0 / 1002/2OK17.7s492 / 271
CG-AL-M034medium262.5 / 1001/2OK24.0s1.8k / 856
CG-AL-M035medium1100.0 / 1002/2OK19.8s358 / 98
CG-AL-M036medium2100.0 / 1002/2OK19.5s1.8k / 750
CG-AL-M037medium20.0 / 1000/0FAIL9.1s1.5k / 565
CG-AL-M038medium1100.0 / 1002/2OK16.6s433 / 180
CG-AL-M039medium20.0 / 1000/0FAIL17.5s2.2k / 1.8k
CG-AL-M040medium20.0 / 1000/0FAIL8.1s899 / 408
CG-AL-M041medium1100.0 / 1003/3OK16.1s345 / 119
CG-AL-M042medium2100.0 / 1008/8OK19.0s1.8k / 688
CG-AL-M043medium1100.0 / 1005/5OK20.5s483 / 374
CG-AL-M044medium1100.0 / 1006/6OK2m 33s719 / 641
CG-AL-M045medium1100.0 / 1006/6OK16.7s776 / 183
CG-AL-M088medium1100.0 / 1006/6OK19.8s451 / 450
CG-AL-M112medium1100.0 / 1004/4OK23.1s620 / 735