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.

84.5% 93/110 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.

67.0 / 100
Cost $0.98
Tokens 122k / 89k input / output, all attempts
Duration 6h 55m
Filter:
Per-task results for run 473921f2-69d2-42d2-ae94-87d90f38af53
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK38.6s265 / 256
CG-AL-E002easy1100.0 / 1006/6OK2m 44s278 / 242
CG-AL-E003easy1100.0 / 1005/5OK35.6s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK47.8s288 / 229
CG-AL-E005easy1100.0 / 10013/13OK54.0s299 / 235
CG-AL-E006easy2100.0 / 1007/7OK4m 3s2.1k / 602
CG-AL-E007easy1100.0 / 1007/7OK1m 23s348 / 163
CG-AL-E008easy1100.0 / 1006/6OK2m 3s271 / 297
CG-AL-E009easy1100.0 / 1005/5OK1m 59s274 / 190
CG-AL-E010easy1100.0 / 1005/5OK2m 8s278 / 133
CG-AL-E031easy1100.0 / 1003/3OK2m 7s408 / 466
CG-AL-E032easy1100.0 / 1001/1OK2m 13s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK21.9s362 / 350
CG-AL-E050easy20.0 / 1000/0FAIL26.8s2.1k / 405
CG-AL-E051easy1100.0 / 10015/15OK1m 8s488 / 789
CG-AL-E052easy2100.0 / 10016/16OK15m 41s1.6k / 470
CG-AL-E053easy1100.0 / 1003/3OK2m 42s303 / 140
CG-AL-E054easy2100.0 / 1009/9OK1m 24s1.3k / 861
CG-AL-E055easy1100.0 / 1008/8OK1m 36s344 / 189
CG-AL-E056easy2100.0 / 10015/15OK12m 34s1.9k / 665
CG-AL-E057easy20.0 / 1000/0FAIL24m 56s1.4k / 957
CG-AL-E058easy2100.0 / 1001/1OK12m 35s912 / 339
CG-AL-H001hard1100.0 / 10025/25OK20m 54s470 / 324
CG-AL-H002hard1100.0 / 1004/4OK19m 15s448 / 559
CG-AL-H003hard1100.0 / 1005/5OK20m 1s491 / 712
CG-AL-H004hard2100.0 / 10014/14OK2m 2s1.5k / 849
CG-AL-H005hard1100.0 / 1006/6OK16m 14s724 / 975
CG-AL-H006hard1100.0 / 1006/6OK15m 52s420 / 227
CG-AL-H007hard1100.0 / 10010/10OK11m 13s558 / 529
CG-AL-H008hard2100.0 / 10010/10OK4m 8s1.6k / 704
CG-AL-H009hard1100.0 / 10011/11OK4m 14s600 / 485
CG-AL-H010hard1100.0 / 1008/8OK2m 2s522 / 366
CG-AL-H011hard2100.0 / 1005/5OK36.4s987 / 418
CG-AL-H013hard1100.0 / 1009/9OK49.4s371 / 317
CG-AL-H014hard20.0 / 1000/0FAIL15.3s1.5k / 874
CG-AL-H015hard1100.0 / 1004/4OK37.7s408 / 316
CG-AL-H016hard1100.0 / 1004/4OK17.7s407 / 277
CG-AL-H017hard2100.0 / 1003/3OK1m 23s1.0k / 515
CG-AL-H018hard1100.0 / 1006/6OK49.1s424 / 506
CG-AL-H019hard1100.0 / 1005/5OK1m 17s318 / 162
CG-AL-H020hard2100.0 / 10010/10OK26.8s1.9k / 1.6k
CG-AL-H021hard2100.0 / 10020/20OK2m 27s17k / 1.5k
CG-AL-H022hard1100.0 / 10021/21OK43.7s760 / 944
CG-AL-H023hard20.0 / 1000/0FAIL1m 36s4.1k / 9.6k
CG-AL-H024hard1100.0 / 1009/9OK47.6s529 / 864
CG-AL-H025hard1100.0 / 1007/7OK57.3s372 / 282
CG-AL-H026hard1100.0 / 1008/8OK43.5s467 / 240
CG-AL-H027hard1100.0 / 1004/4OK24.1s785 / 188
CG-AL-H028hard1100.0 / 1009/9OK22.7s647 / 486
CG-AL-H029hard2100.0 / 10018/18OK1m 38s3.0k / 2.5k
CG-AL-H030hard1100.0 / 10010/10OK1m 44s698 / 772
CG-AL-H031hard1100.0 / 10022/22OK2m 27s995 / 1.1k
CG-AL-H032hard1100.0 / 10019/19OK3m 45s749 / 992
CG-AL-H033hard1100.0 / 1005/5OK3m 33s799 / 1.6k
CG-AL-H034hard2100.0 / 1003/3OK41.4s1.5k / 347
CG-AL-H035hard1100.0 / 1003/3OK19.7s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK28.9s994 / 325
CG-AL-H037hard1100.0 / 1003/3OK49.7s514 / 176
CG-AL-H038hard1100.0 / 1003/3OK50.2s580 / 235
CG-AL-H039hard1100.0 / 1004/4OK18.6s489 / 211
CG-AL-H040hard1100.0 / 1002/2OK18.9s403 / 160
CG-AL-H041hard1100.0 / 1003/3OK1m 6s620 / 439
CG-AL-H042hard2100.0 / 1003/3OK17.6s954 / 202
CG-AL-H043hard1100.0 / 1005/5OK16.4s399 / 90
CG-AL-H050hard20.0 / 1000/0FAIL4m 17s1.3k / 404
CG-AL-H051hard1100.0 / 1004/4OK39.4s664 / 136
CG-AL-H052hard1100.0 / 1005/5OK1m 33s726 / 104
CG-AL-H053hard1100.0 / 1004/4OK27.7s570 / 241
CG-AL-H054hard20.0 / 1000/0FAIL13.6s2.0k / 648
CG-AL-H056hard20.0 / 1000/0FAIL4m 15s1.6k / 580
CG-AL-H057hard1100.0 / 1004/4OK2m 40s728 / 277
CG-AL-H058hard1100.0 / 1005/5OK1m 38s604 / 324
CG-AL-H205hard1100.0 / 1006/6OK20.9s447 / 392
CG-AL-M001medium20.0 / 1000/0FAIL13.6s1.5k / 854
CG-AL-M002medium2100.0 / 10022/22OK21.0s1.4k / 928
CG-AL-M003medium262.5 / 1003/9OK22.2s1.6k / 1.3k
CG-AL-M004medium2100.0 / 10012/12OK2m 53s1.8k / 2.4k
CG-AL-M005medium1100.0 / 10022/22OK40.0s570 / 1.4k
CG-AL-M006medium2100.0 / 10018/18OK52.3s2.7k / 2.3k
CG-AL-M007medium2100.0 / 10015/15OK1m 3s2.2k / 3.5k
CG-AL-M008medium262.5 / 1002/12OK1m 8s2.3k / 5.3k
CG-AL-M009medium1100.0 / 10011/11OK37.2s439 / 1.6k
CG-AL-M010medium2100.0 / 10021/21OK3m 0s2.6k / 3.6k
CG-AL-M020medium2100.0 / 10017/17OK20.9s2.2k / 1.3k
CG-AL-M021medium1100.0 / 10011/11OK29.1s560 / 498
CG-AL-M022medium1100.0 / 1009/9OK24.8s524 / 658
CG-AL-M023medium262.5 / 10010/11OK2m 31s1.8k / 1.2k
CG-AL-M024medium1100.0 / 10010/10OK47.2s511 / 985
CG-AL-M025medium1100.0 / 1007/7OK21.8s421 / 351
CG-AL-M026medium1100.0 / 1008/8OK34.0s383 / 363
CG-AL-M027medium2100.0 / 10018/18OK39.4s3.9k / 3.8k
CG-AL-M028medium20.0 / 1000/0FAIL18.8s1.1k / 548
CG-AL-M029medium2100.0 / 1003/3OK2m 55s920 / 188
CG-AL-M031medium20.0 / 1000/0FAIL41.0s2.8k / 1.4k
CG-AL-M032medium1100.0 / 1003/3OK37.7s510 / 186
CG-AL-M033medium1100.0 / 1002/2OK53.1s449 / 236
CG-AL-M034medium262.5 / 1001/2OK4m 1s1.9k / 771
CG-AL-M035medium1100.0 / 1002/2OK30.3s328 / 90
CG-AL-M036medium20.0 / 1000/0FAIL4m 21s1.6k / 1.5k
CG-AL-M037medium20.0 / 1000/0FAIL10m 45s2.5k / 3.1k
CG-AL-M038medium1100.0 / 1002/2OK2m 54s399 / 165
CG-AL-M039medium1100.0 / 1002/2OK3m 31s468 / 352
CG-AL-M040medium262.5 / 1001/2OK12m 44s851 / 383
CG-AL-M041medium1100.0 / 1003/3OK8m 43s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK5m 19s520 / 286
CG-AL-M043medium1100.0 / 1005/5OK5m 16s472 / 263
CG-AL-M044medium1100.0 / 1006/6OK3m 5s654 / 544
CG-AL-M045medium1100.0 / 1006/6OK45.4s729 / 154
CG-AL-M088medium1100.0 / 1006/6OK38.6s407 / 423
CG-AL-M112medium1100.0 / 1004/4OK11m 27s581 / 678