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.

85.5% 94/110 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.

73.4 / 100
Cost $1.11
Tokens 111k / 74k input / output, all attempts
Duration 5h 11m
Filter:
Per-task results for run cd36fbe5-aafa-444b-9293-23420b1517cb
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK21.3s265 / 220
CG-AL-E002easy1100.0 / 1006/6OK2m 38s278 / 241
CG-AL-E003easy1100.0 / 1005/5OK40.6s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK42.3s288 / 227
CG-AL-E005easy1100.0 / 10013/13OK51.8s299 / 264
CG-AL-E006easy1100.0 / 1007/7OK3m 47s289 / 355
CG-AL-E007easy1100.0 / 1007/7OK1m 14s348 / 154
CG-AL-E008easy1100.0 / 1006/6OK1m 31s271 / 290
CG-AL-E009easy1100.0 / 1005/5OK1m 44s274 / 174
CG-AL-E010easy1100.0 / 1005/5OK1m 54s278 / 111
CG-AL-E031easy1100.0 / 1003/3OK2m 4s408 / 473
CG-AL-E032easy1100.0 / 1001/1OK1m 59s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK25.1s362 / 339
CG-AL-E050easy20.0 / 1000/0FAIL21.2s2.1k / 387
CG-AL-E051easy1100.0 / 10015/15OK44.7s488 / 770
CG-AL-E052easy2100.0 / 10016/16OK6m 26s1.6k / 470
CG-AL-E053easy1100.0 / 1003/3OK2m 49s303 / 138
CG-AL-E054easy1100.0 / 1009/9OK6m 13s404 / 453
CG-AL-E055easy1100.0 / 1008/8OK24.5s344 / 211
CG-AL-E056easy2100.0 / 10015/15OK5m 25s1.9k / 665
CG-AL-E057easy20.0 / 1000/0FAIL11m 49s2.5k / 789
CG-AL-E058easy2100.0 / 1001/1OK1m 25s911 / 203
CG-AL-H001hard1100.0 / 10025/25OK9m 56s470 / 272
CG-AL-H002hard1100.0 / 1004/4OK10m 11s448 / 541
CG-AL-H003hard1100.0 / 1005/5OK9m 31s491 / 572
CG-AL-H004hard1100.0 / 10014/14OK8m 7s502 / 415
CG-AL-H005hard1100.0 / 1006/6OK8m 13s724 / 532
CG-AL-H006hard1100.0 / 1006/6OK1m 13s420 / 228
CG-AL-H007hard1100.0 / 10010/10OK7m 36s558 / 623
CG-AL-H008hard1100.0 / 10010/10OK3m 29s516 / 354
CG-AL-H009hard1100.0 / 10011/11OK9m 29s600 / 517
CG-AL-H010hard1100.0 / 1008/8OK23.3s522 / 364
CG-AL-H011hard2100.0 / 1005/5OK24.5s979 / 398
CG-AL-H013hard1100.0 / 1009/9OK44.7s371 / 335
CG-AL-H014hard1100.0 / 1007/7OK1m 11s448 / 948
CG-AL-H015hard1100.0 / 1004/4OK21.3s408 / 263
CG-AL-H016hard1100.0 / 1004/4OK27.3s407 / 249
CG-AL-H017hard2100.0 / 1003/3OK27.4s1.0k / 533
CG-AL-H018hard1100.0 / 1006/6OK55.0s424 / 600
CG-AL-H019hard1100.0 / 1005/5OK23.8s318 / 152
CG-AL-H020hard1100.0 / 10010/10OK37.7s479 / 703
CG-AL-H021hard2100.0 / 10020/20OK32.8s17k / 1.4k
CG-AL-H022hard1100.0 / 10021/21OK39.9s760 / 946
CG-AL-H023hard20.0 / 1000/0FAIL1m 43s3.7k / 6.8k
CG-AL-H024hard1100.0 / 1009/9OK1m 5s529 / 708
CG-AL-H025hard1100.0 / 1007/7OK53.6s372 / 180
CG-AL-H026hard1100.0 / 1008/8OK26.2s467 / 285
CG-AL-H027hard2100.0 / 1004/4OK53.6s2.4k / 369
CG-AL-H028hard1100.0 / 1009/9OK25.4s647 / 486
CG-AL-H029hard2100.0 / 10018/18OK43.6s2.8k / 2.2k
CG-AL-H030hard2100.0 / 10010/10OK44.7s2.2k / 1.4k
CG-AL-H031hard1100.0 / 10022/22OK55.6s995 / 1.2k
CG-AL-H032hard1100.0 / 10019/19OK32.4s749 / 947
CG-AL-H033hard1100.0 / 1005/5OK2m 50s799 / 1.6k
CG-AL-H034hard262.5 / 1002/3OK32.8s1.2k / 299
CG-AL-H035hard1100.0 / 1003/3OK19.9s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK6m 41s995 / 322
CG-AL-H037hard20.0 / 1000/0FAIL29.5s1.2k / 371
CG-AL-H038hard1100.0 / 1003/3OK31.6s580 / 227
CG-AL-H039hard1100.0 / 1004/4OK25.0s489 / 253
CG-AL-H040hard1100.0 / 1002/2OK19.6s403 / 161
CG-AL-H041hard1100.0 / 1003/3OK1m 10s620 / 384
CG-AL-H042hard1100.0 / 1003/3OK19.7s403 / 102
CG-AL-H043hard1100.0 / 1005/5OK19.2s399 / 89
CG-AL-H050hard1100.0 / 1003/3OK50.0s530 / 175
CG-AL-H051hard1100.0 / 1004/4OK23.0s664 / 136
CG-AL-H052hard1100.0 / 1005/5OK27.3s726 / 104
CG-AL-H053hard1100.0 / 1004/4OK22.4s570 / 234
CG-AL-H054hard20.0 / 1000/0FAIL22.3s2.0k / 594
CG-AL-H056hard2100.0 / 1004/4OK53.3s1.6k / 311
CG-AL-H057hard1100.0 / 1004/4OK2m 46s728 / 307
CG-AL-H058hard1100.0 / 1005/5OK25.8s604 / 302
CG-AL-H205hard1100.0 / 1006/6OK30.4s447 / 382
CG-AL-M001medium20.0 / 1000/0FAIL16.5s1.5k / 848
CG-AL-M002medium1100.0 / 10022/22OK26.9s423 / 443
CG-AL-M003medium1100.0 / 1009/9OK49.3s434 / 572
CG-AL-M004medium1100.0 / 10012/12OK3m 8s456 / 1.2k
CG-AL-M005medium1100.0 / 10022/22OK41.0s570 / 1.1k
CG-AL-M006medium262.5 / 10017/18OK56.6s2.7k / 2.3k
CG-AL-M007medium20.0 / 1000/0FAIL53.9s2.2k / 2.8k
CG-AL-M008medium20.0 / 1000/0FAIL1m 20s4.0k / 4.7k
CG-AL-M009medium1100.0 / 10011/11OK1m 11s439 / 1.3k
CG-AL-M010medium1100.0 / 10021/21OK2m 54s646 / 1.8k
CG-AL-M020medium1100.0 / 10017/17OK32.7s581 / 684
CG-AL-M021medium1100.0 / 10011/11OK27.8s560 / 515
CG-AL-M022medium1100.0 / 1009/9OK29.0s524 / 661
CG-AL-M023medium262.5 / 10010/11OK9m 6s1.8k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK31.8s511 / 1.0k
CG-AL-M025medium2100.0 / 1007/7OK38.9s3.0k / 644
CG-AL-M026medium1100.0 / 1008/8OK11m 59s1.0k / 2.9k
CG-AL-M027medium1100.0 / 10018/18OK53.5s747 / 1.6k
CG-AL-M028medium2100.0 / 1003/3OK3m 6s1.1k / 552
CG-AL-M029medium20.0 / 1000/0FAIL44.8s936 / 216
CG-AL-M031medium2100.0 / 1002/2OK1m 27s2.8k / 1.4k
CG-AL-M032medium1100.0 / 1003/3OK8m 22s510 / 192
CG-AL-M033medium1100.0 / 1002/2OK6m 18s449 / 236
CG-AL-M034medium262.5 / 1001/2OK1m 8s1.4k / 409
CG-AL-M035medium1100.0 / 1002/2OK18.4s328 / 87
CG-AL-M036medium20.0 / 1000/0FAIL6m 47s1.6k / 734
CG-AL-M037medium20.0 / 1000/0FAIL14m 51s1.4k / 1.4k
CG-AL-M038medium1100.0 / 1002/2OK7m 5s399 / 161
CG-AL-M039medium1100.0 / 1002/2OK9m 38s468 / 404
CG-AL-M040medium20.0 / 1000/0FAIL40.5s1.1k / 319
CG-AL-M041medium1100.0 / 1003/3OK1m 48s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK1m 32s520 / 248
CG-AL-M043medium1100.0 / 1005/5OK48.3s472 / 236
CG-AL-M044medium1100.0 / 1006/6OK2m 30s654 / 569
CG-AL-M045medium1100.0 / 1006/6OK46.5s729 / 136
CG-AL-M088medium1100.0 / 1006/6OK31.9s407 / 434
CG-AL-M112medium1100.0 / 1004/4OK31.6s581 / 671