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.

89.1% 98/110 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.

73.3 / 100
Cost $1.11
Tokens 113k / 74k input / output, all attempts
Duration 6h 25m
Filter:
Per-task results for run a6a3e726-acac-446e-bd42-96933e5ee957
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK21.2s265 / 220
CG-AL-E002easy1100.0 / 1006/6OK2m 56s278 / 241
CG-AL-E003easy1100.0 / 1005/5OK34.8s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK48.8s288 / 227
CG-AL-E005easy1100.0 / 10013/13OK54.8s299 / 259
CG-AL-E006easy2100.0 / 1007/7OK9m 18s2.1k / 542
CG-AL-E007easy1100.0 / 1007/7OK1m 20s348 / 146
CG-AL-E008easy1100.0 / 1006/6OK1m 48s271 / 285
CG-AL-E009easy1100.0 / 1005/5OK2m 8s274 / 198
CG-AL-E010easy1100.0 / 1005/5OK2m 16s278 / 113
CG-AL-E031easy1100.0 / 1003/3OK2m 19s408 / 441
CG-AL-E032easy1100.0 / 1001/1OK2m 20s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK21.4s362 / 290
CG-AL-E050easy20.0 / 1000/0FAIL1m 58s2.1k / 450
CG-AL-E051easy1100.0 / 10015/15OK34.8s488 / 796
CG-AL-E052easy2100.0 / 10016/16OK4m 19s1.6k / 470
CG-AL-E053easy1100.0 / 1003/3OK2m 36s303 / 137
CG-AL-E054easy2100.0 / 1009/9OK10m 39s1.4k / 917
CG-AL-E055easy1100.0 / 1008/8OK23.6s344 / 211
CG-AL-E056easy2100.0 / 10015/15OK32.8s1.9k / 665
CG-AL-E057easy20.0 / 1000/0FAIL1m 20s1.5k / 692
CG-AL-E058easy2100.0 / 1001/1OK14m 10s912 / 200
CG-AL-H001hard1100.0 / 10025/25OK4m 17s470 / 272
CG-AL-H002hard1100.0 / 1004/4OK5m 45s448 / 541
CG-AL-H003hard1100.0 / 1005/5OK1m 13s491 / 556
CG-AL-H004hard1100.0 / 10014/14OK9m 2s502 / 384
CG-AL-H005hard1100.0 / 1006/6OK11m 38s724 / 527
CG-AL-H006hard1100.0 / 1006/6OK12m 51s420 / 228
CG-AL-H007hard1100.0 / 10010/10OK15m 47s558 / 624
CG-AL-H008hard1100.0 / 10010/10OK9m 16s516 / 360
CG-AL-H009hard1100.0 / 10011/11OK33.9s600 / 517
CG-AL-H010hard1100.0 / 1008/8OK4m 13s522 / 364
CG-AL-H011hard1100.0 / 1005/5OK37.0s365 / 192
CG-AL-H013hard1100.0 / 1009/9OK37.1s371 / 341
CG-AL-H014hard2100.0 / 1007/7OK6m 33s1.3k / 1.0k
CG-AL-H015hard1100.0 / 1004/4OK1m 34s408 / 263
CG-AL-H016hard1100.0 / 1004/4OK1m 2s407 / 248
CG-AL-H017hard2100.0 / 1003/3OK1m 41s1.0k / 503
CG-AL-H018hard1100.0 / 1006/6OK1m 35s424 / 675
CG-AL-H019hard1100.0 / 1005/5OK31.0s318 / 152
CG-AL-H020hard1100.0 / 10010/10OK59.5s479 / 720
CG-AL-H021hard2100.0 / 10020/20OK1m 38s18k / 1.5k
CG-AL-H022hard1100.0 / 10021/21OK2m 16s760 / 909
CG-AL-H023hard20.0 / 1000/0FAIL2m 3s4.0k / 8.0k
CG-AL-H024hard1100.0 / 1009/9OK1m 13s529 / 742
CG-AL-H025hard1100.0 / 1007/7OK49.0s372 / 176
CG-AL-H026hard1100.0 / 1008/8OK29.2s467 / 283
CG-AL-H027hard2100.0 / 1004/4OK53.5s2.4k / 332
CG-AL-H028hard1100.0 / 1009/9OK39.5s647 / 486
CG-AL-H029hard2100.0 / 10018/18OK6m 10s3.0k / 2.3k
CG-AL-H030hard2100.0 / 10010/10OK44.7s2.1k / 1.4k
CG-AL-H031hard2100.0 / 10022/22OK1m 34s3.3k / 2.3k
CG-AL-H032hard1100.0 / 10019/19OK1m 32s749 / 979
CG-AL-H033hard1100.0 / 1005/5OK2m 53s799 / 1.6k
CG-AL-H034hard2100.0 / 1003/3OK21.5s1.6k / 459
CG-AL-H035hard1100.0 / 1003/3OK18.2s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK6m 35s991 / 322
CG-AL-H037hard2100.0 / 1003/3OK26.8s1.2k / 370
CG-AL-H038hard1100.0 / 1003/3OK32.7s580 / 242
CG-AL-H039hard1100.0 / 1004/4OK24.3s489 / 249
CG-AL-H040hard1100.0 / 1002/2OK21.6s403 / 161
CG-AL-H041hard1100.0 / 1003/3OK1m 38s620 / 392
CG-AL-H042hard1100.0 / 1003/3OK19.8s403 / 102
CG-AL-H043hard1100.0 / 1005/5OK18.2s399 / 90
CG-AL-H050hard1100.0 / 1003/3OK43.4s530 / 186
CG-AL-H051hard1100.0 / 1004/4OK24.8s664 / 131
CG-AL-H052hard1100.0 / 1005/5OK40.0s726 / 104
CG-AL-H053hard1100.0 / 1004/4OK21.7s570 / 236
CG-AL-H054hard2100.0 / 1005/5OK50.4s1.6k / 608
CG-AL-H056hard2100.0 / 1004/4OK42.6s1.6k / 311
CG-AL-H057hard1100.0 / 1004/4OK2m 51s728 / 307
CG-AL-H058hard1100.0 / 1005/5OK1m 4s604 / 302
CG-AL-H205hard1100.0 / 1006/6OK26.7s447 / 372
CG-AL-M001medium20.0 / 1000/0FAIL32.8s1.4k / 942
CG-AL-M002medium1100.0 / 10022/22OK28.9s423 / 435
CG-AL-M003medium1100.0 / 1009/9OK36.0s434 / 563
CG-AL-M004medium1100.0 / 10012/12OK3m 7s456 / 1.2k
CG-AL-M005medium1100.0 / 10022/22OK35.6s570 / 1.2k
CG-AL-M006medium1100.0 / 10018/18OK51.0s435 / 1.2k
CG-AL-M007medium20.0 / 1000/0FAIL37.5s2.3k / 2.8k
CG-AL-M008medium20.0 / 1000/0FAIL6m 41s2.5k / 5.2k
CG-AL-M009medium1100.0 / 10011/11OK38.2s439 / 1.3k
CG-AL-M010medium1100.0 / 10021/21OK2m 57s646 / 1.9k
CG-AL-M020medium1100.0 / 10017/17OK1m 17s581 / 710
CG-AL-M021medium1100.0 / 10011/11OK52.7s560 / 536
CG-AL-M022medium1100.0 / 1009/9OK27.3s524 / 611
CG-AL-M023medium262.5 / 10010/11OK2m 42s1.8k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK31.7s511 / 795
CG-AL-M025medium2100.0 / 1007/7OK2m 19s3.0k / 728
CG-AL-M026medium1100.0 / 1008/8OK6m 50s383 / 356
CG-AL-M027medium1100.0 / 10018/18OK2m 31s747 / 1.6k
CG-AL-M028medium2100.0 / 1003/3OK2m 31s1.1k / 551
CG-AL-M029medium2100.0 / 1003/3OK3m 35s919 / 180
CG-AL-M031medium20.0 / 1000/0FAIL7m 3s2.8k / 1.5k
CG-AL-M032medium1100.0 / 1003/3OK24.1s510 / 191
CG-AL-M033medium1100.0 / 1002/2OK2m 52s449 / 236
CG-AL-M034medium262.5 / 1001/2OK5m 49s1.4k / 441
CG-AL-M035medium1100.0 / 1002/2OK2m 30s328 / 87
CG-AL-M036medium20.0 / 1000/0FAIL6m 17s1.6k / 674
CG-AL-M037medium20.0 / 1000/0FAIL6m 32s1.4k / 419
CG-AL-M038medium1100.0 / 1002/2OK10m 0s399 / 161
CG-AL-M039medium2100.0 / 1002/2OK3m 20s2.2k / 1.2k
CG-AL-M040medium20.0 / 1000/0FAIL6m 49s1.1k / 319
CG-AL-M041medium1100.0 / 1003/3OK1m 1s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK1m 0s520 / 261
CG-AL-M043medium1100.0 / 1005/5OK6m 47s472 / 263
CG-AL-M044medium1100.0 / 1006/6OK7m 39s654 / 522
CG-AL-M045medium1100.0 / 1006/6OK5m 5s729 / 160
CG-AL-M088medium1100.0 / 1006/6OK3m 25s407 / 399
CG-AL-M112medium1100.0 / 1004/4OK3m 45s581 / 671