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.

66.5 / 100
Cost $0.92
Tokens 120k / 82k input / output, all attempts
Duration 5h 13m
Filter:
Per-task results for run 1cd7680d-0bea-4d96-af28-fca3f0e75b7d
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK19.0s265 / 256
CG-AL-E002easy1100.0 / 1006/6OK2m 38s278 / 242
CG-AL-E003easy1100.0 / 1005/5OK35.6s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK41.3s288 / 229
CG-AL-E005easy1100.0 / 10013/13OK1m 1s299 / 261
CG-AL-E006easy2100.0 / 1007/7OK4m 1s2.0k / 619
CG-AL-E007easy1100.0 / 1007/7OK1m 24s348 / 163
CG-AL-E008easy1100.0 / 1006/6OK2m 0s271 / 268
CG-AL-E009easy1100.0 / 1005/5OK2m 8s274 / 190
CG-AL-E010easy1100.0 / 1005/5OK2m 12s278 / 133
CG-AL-E031easy1100.0 / 1003/3OK2m 16s408 / 420
CG-AL-E032easy1100.0 / 1001/1OK2m 17s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK29.8s362 / 340
CG-AL-E050easy20.0 / 1000/0FAIL20.0s2.1k / 398
CG-AL-E051easy1100.0 / 10015/15OK32.9s488 / 699
CG-AL-E052easy2100.0 / 10016/16OK4m 30s1.6k / 494
CG-AL-E053easy1100.0 / 1003/3OK2m 30s303 / 140
CG-AL-E054easy1100.0 / 1009/9OK21.9s404 / 197
CG-AL-E055easy1100.0 / 1008/8OK29.6s344 / 189
CG-AL-E056easy2100.0 / 10015/15OK9m 54s1.9k / 701
CG-AL-E057easy20.0 / 1000/0FAIL8m 1s1.4k / 686
CG-AL-E058easy2100.0 / 1001/1OK5m 16s912 / 272
CG-AL-H001hard1100.0 / 10025/25OK5m 34s470 / 298
CG-AL-H002hard1100.0 / 1004/4OK5m 53s448 / 558
CG-AL-H003hard1100.0 / 1005/5OK4m 10s491 / 554
CG-AL-H004hard1100.0 / 10014/14OK9m 9s502 / 412
CG-AL-H005hard2100.0 / 1006/6OK2m 10s2.5k / 1.9k
CG-AL-H006hard1100.0 / 1006/6OK12m 56s420 / 225
CG-AL-H007hard1100.0 / 10010/10OK9m 53s558 / 608
CG-AL-H008hard1100.0 / 10010/10OK9m 25s516 / 336
CG-AL-H009hard1100.0 / 10011/11OK4m 11s600 / 469
CG-AL-H010hard1100.0 / 1008/8OK4m 28s522 / 364
CG-AL-H011hard2100.0 / 1005/5OK2m 21s989 / 418
CG-AL-H013hard1100.0 / 1009/9OK42.8s371 / 310
CG-AL-H014hard20.0 / 1000/0FAIL2m 33s1.5k / 837
CG-AL-H015hard1100.0 / 1004/4OK1m 40s408 / 275
CG-AL-H016hard1100.0 / 1004/4OK1m 15s407 / 283
CG-AL-H017hard2100.0 / 1003/3OK1m 39s1.0k / 529
CG-AL-H018hard1100.0 / 1006/6OK1m 51s424 / 470
CG-AL-H019hard1100.0 / 1005/5OK38.1s318 / 159
CG-AL-H020hard2100.0 / 10010/10OK1m 13s1.9k / 1.5k
CG-AL-H021hard2100.0 / 10020/20OK43.5s17k / 1.4k
CG-AL-H022hard1100.0 / 10021/21OK1m 27s760 / 1.0k
CG-AL-H023hard20.0 / 1000/0FAIL1m 34s3.7k / 8.9k
CG-AL-H024hard1100.0 / 1009/9OK1m 13s529 / 893
CG-AL-H025hard1100.0 / 1007/7OK47.0s372 / 249
CG-AL-H026hard1100.0 / 1008/8OK26.5s467 / 274
CG-AL-H027hard2100.0 / 1004/4OK38.2s2.4k / 344
CG-AL-H028hard1100.0 / 1009/9OK40.4s647 / 486
CG-AL-H029hard20.0 / 1000/0FAIL30.5s2.9k / 2.3k
CG-AL-H030hard1100.0 / 10010/10OK1m 24s698 / 760
CG-AL-H031hard1100.0 / 10022/22OK1m 15s995 / 1.1k
CG-AL-H032hard2100.0 / 10019/19OK38.9s2.8k / 1.8k
CG-AL-H033hard1100.0 / 1005/5OK2m 57s799 / 1.6k
CG-AL-H034hard2100.0 / 1003/3OK16.1s1.4k / 309
CG-AL-H035hard1100.0 / 1003/3OK16.6s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK25.5s997 / 325
CG-AL-H037hard2100.0 / 1003/3OK26.3s1.3k / 408
CG-AL-H038hard1100.0 / 1003/3OK26.6s580 / 235
CG-AL-H039hard1100.0 / 1004/4OK17.5s489 / 254
CG-AL-H040hard1100.0 / 1002/2OK17.9s403 / 157
CG-AL-H041hard1100.0 / 1003/3OK33.7s620 / 407
CG-AL-H042hard2100.0 / 1003/3OK16.5s954 / 202
CG-AL-H043hard1100.0 / 1005/5OK15.8s399 / 90
CG-AL-H050hard20.0 / 1000/0FAIL25.9s1.3k / 386
CG-AL-H051hard1100.0 / 1004/4OK21.3s664 / 136
CG-AL-H052hard1100.0 / 1005/5OK42.2s726 / 104
CG-AL-H053hard1100.0 / 1004/4OK19.6s570 / 241
CG-AL-H054hard20.0 / 1000/0FAIL13.8s2.0k / 648
CG-AL-H056hard20.0 / 1000/0FAIL12.8s1.6k / 314
CG-AL-H057hard1100.0 / 1004/4OK2m 30s728 / 277
CG-AL-H058hard1100.0 / 1005/5OK42.4s604 / 321
CG-AL-H205hard1100.0 / 1006/6OK20.2s447 / 425
CG-AL-M001medium20.0 / 1000/0FAIL11.5s1.5k / 854
CG-AL-M002medium2100.0 / 10022/22OK19.5s1.4k / 926
CG-AL-M003medium1100.0 / 1009/9OK30.7s434 / 649
CG-AL-M004medium1100.0 / 10012/12OK2m 46s456 / 1.3k
CG-AL-M005medium1100.0 / 10022/22OK34.1s570 / 1.3k
CG-AL-M006medium262.5 / 10017/18OK44.8s3.0k / 2.6k
CG-AL-M007medium20.0 / 1000/0FAIL37.5s2.0k / 2.9k
CG-AL-M008medium262.5 / 1009/12OK2m 1s3.7k / 7.3k
CG-AL-M009medium1100.0 / 10011/11OK58.6s439 / 1.5k
CG-AL-M010medium1100.0 / 10021/21OK3m 30s646 / 1.8k
CG-AL-M020medium2100.0 / 10017/17OK24.4s2.0k / 1.4k
CG-AL-M021medium1100.0 / 10011/11OK45.1s560 / 506
CG-AL-M022medium1100.0 / 1009/9OK22.6s524 / 627
CG-AL-M023medium262.5 / 10010/11OK3m 1s1.8k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK25.3s511 / 1.0k
CG-AL-M025medium1100.0 / 1007/7OK21.6s421 / 363
CG-AL-M026medium1100.0 / 1008/8OK24.3s383 / 349
CG-AL-M027medium262.5 / 10014/18OK34.5s3.9k / 3.6k
CG-AL-M028medium20.0 / 1000/0FAIL21.9s1.1k / 558
CG-AL-M029medium20.0 / 1000/0FAIL26.3s936 / 216
CG-AL-M031medium20.0 / 1000/0FAIL27.9s2.9k / 1.5k
CG-AL-M032medium1100.0 / 1003/3OK33.6s510 / 186
CG-AL-M033medium1100.0 / 1002/2OK2m 59s449 / 239
CG-AL-M034medium262.5 / 1001/2OK4m 34s1.5k / 1.1k
CG-AL-M035medium1100.0 / 1002/2OK2m 29s328 / 87
CG-AL-M036medium20.0 / 1000/0FAIL3m 52s1.6k / 696
CG-AL-M037medium20.0 / 1000/0FAIL51.4s1.4k / 442
CG-AL-M038medium1100.0 / 1002/2OK9m 55s399 / 171
CG-AL-M039medium1100.0 / 1002/2OK11m 25s468 / 345
CG-AL-M040medium262.5 / 1001/2OK42.3s851 / 321
CG-AL-M041medium1100.0 / 1003/3OK58.0s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK58.5s520 / 319
CG-AL-M043medium1100.0 / 1005/5OK7m 0s472 / 263
CG-AL-M044medium1100.0 / 1006/6OK7m 26s654 / 527
CG-AL-M045medium1100.0 / 1006/6OK1m 13s729 / 166
CG-AL-M088medium1100.0 / 1006/6OK3m 33s407 / 404
CG-AL-M112medium1100.0 / 1004/4OK3m 56s581 / 703