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.

88.2% 97/110 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.

75.1 / 100
Cost $1.02
Tokens 109k / 67k input / output, all attempts
Duration 6h 23m
Filter:
Per-task results for run 97865fb5-e261-41ea-93a8-9e3be118c978
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK41.3s265 / 222
CG-AL-E002easy1100.0 / 1006/6OK3m 4s278 / 241
CG-AL-E003easy1100.0 / 1005/5OK41.9s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK47.9s288 / 234
CG-AL-E005easy1100.0 / 10013/13OK56.3s299 / 263
CG-AL-E006easy2100.0 / 1007/7OK3m 40s2.0k / 567
CG-AL-E007easy1100.0 / 1007/7OK1m 18s348 / 187
CG-AL-E008easy1100.0 / 1006/6OK1m 37s271 / 281
CG-AL-E009easy1100.0 / 1005/5OK1m 53s274 / 174
CG-AL-E010easy1100.0 / 1005/5OK2m 8s278 / 113
CG-AL-E031easy1100.0 / 1003/3OK2m 16s408 / 441
CG-AL-E032easy1100.0 / 1001/1OK2m 12s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK23.0s362 / 339
CG-AL-E050easy20.0 / 1000/0FAIL6m 23s2.1k / 479
CG-AL-E051easy1100.0 / 10015/15OK49.5s488 / 835
CG-AL-E052easy2100.0 / 10016/16OK19m 38s1.6k / 438
CG-AL-E053easy1100.0 / 1003/3OK2m 35s303 / 138
CG-AL-E054easy2100.0 / 1009/9OK7m 23s1.0k / 394
CG-AL-E055easy1100.0 / 1008/8OK1m 30s344 / 211
CG-AL-E056easy2100.0 / 10015/15OK38.8s1.9k / 665
CG-AL-E057easy20.0 / 1000/0FAIL18m 21s1.4k / 686
CG-AL-E058easy2100.0 / 1001/1OK7m 7s911 / 203
CG-AL-H001hard1100.0 / 10025/25OK20m 46s470 / 297
CG-AL-H002hard1100.0 / 1004/4OK19m 8s448 / 543
CG-AL-H003hard1100.0 / 1005/5OK19m 49s491 / 548
CG-AL-H004hard1100.0 / 10014/14OK20m 8s502 / 413
CG-AL-H005hard1100.0 / 1006/6OK1m 1s724 / 553
CG-AL-H006hard1100.0 / 1006/6OK15m 45s420 / 228
CG-AL-H007hard1100.0 / 10010/10OK6m 36s558 / 587
CG-AL-H008hard1100.0 / 10010/10OK4m 31s516 / 332
CG-AL-H009hard1100.0 / 10011/11OK45.7s600 / 468
CG-AL-H010hard1100.0 / 1008/8OK1m 53s522 / 364
CG-AL-H011hard2100.0 / 1005/5OK47.5s982 / 404
CG-AL-H013hard1100.0 / 1009/9OK55.2s371 / 331
CG-AL-H014hard1100.0 / 1007/7OK51.4s448 / 858
CG-AL-H015hard1100.0 / 1004/4OK34.1s408 / 263
CG-AL-H016hard1100.0 / 1004/4OK23.6s407 / 246
CG-AL-H017hard2100.0 / 1003/3OK1m 12s1.0k / 521
CG-AL-H018hard1100.0 / 1006/6OK1m 29s424 / 434
CG-AL-H019hard1100.0 / 1005/5OK1m 6s318 / 152
CG-AL-H020hard1100.0 / 10010/10OK1m 33s479 / 714
CG-AL-H021hard2100.0 / 10020/20OK3m 24s17k / 1.6k
CG-AL-H022hard1100.0 / 10021/21OK1m 2s760 / 1.0k
CG-AL-H023hard1100.0 / 10025/25OK1m 33s1.2k / 3.8k
CG-AL-H024hard1100.0 / 1009/9OK28.7s529 / 750
CG-AL-H025hard1100.0 / 1007/7OK49.6s372 / 176
CG-AL-H026hard1100.0 / 1008/8OK34.0s467 / 279
CG-AL-H027hard262.5 / 1002/4OK1m 15s2.4k / 306
CG-AL-H028hard1100.0 / 1009/9OK28.1s647 / 486
CG-AL-H029hard2100.0 / 10018/18OK6m 39s2.9k / 2.3k
CG-AL-H030hard2100.0 / 10010/10OK1m 59s2.2k / 1.4k
CG-AL-H031hard1100.0 / 10022/22OK2m 0s995 / 1.1k
CG-AL-H032hard1100.0 / 10019/19OK3m 29s749 / 957
CG-AL-H033hard1100.0 / 1005/5OK3m 2s799 / 1.6k
CG-AL-H034hard2100.0 / 1003/3OK21.2s1.4k / 309
CG-AL-H035hard1100.0 / 1003/3OK18.8s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK7m 28s977 / 284
CG-AL-H037hard2100.0 / 1003/3OK22.4s1.2k / 338
CG-AL-H038hard1100.0 / 1003/3OK32.7s580 / 252
CG-AL-H039hard1100.0 / 1004/4OK25.0s489 / 249
CG-AL-H040hard1100.0 / 1002/2OK29.5s403 / 136
CG-AL-H041hard1100.0 / 1003/3OK42.4s620 / 414
CG-AL-H042hard1100.0 / 1003/3OK20.4s403 / 102
CG-AL-H043hard1100.0 / 1005/5OK19.4s399 / 90
CG-AL-H050hard1100.0 / 1003/3OK55.7s530 / 164
CG-AL-H051hard1100.0 / 1004/4OK26.5s664 / 131
CG-AL-H052hard1100.0 / 1005/5OK1m 11s726 / 158
CG-AL-H053hard1100.0 / 1004/4OK20.8s570 / 243
CG-AL-H054hard20.0 / 1000/0FAIL17.2s2.0k / 594
CG-AL-H056hard2100.0 / 1004/4OK47.3s1.6k / 311
CG-AL-H057hard1100.0 / 1004/4OK2m 32s728 / 305
CG-AL-H058hard1100.0 / 1005/5OK1m 17s604 / 306
CG-AL-H205hard1100.0 / 1006/6OK42.0s447 / 356
CG-AL-M001medium20.0 / 1000/0FAIL17.1s1.5k / 848
CG-AL-M002medium1100.0 / 10022/22OK31.2s423 / 439
CG-AL-M003medium1100.0 / 1009/9OK56.3s434 / 552
CG-AL-M004medium1100.0 / 10012/12OK2m 56s456 / 1.2k
CG-AL-M005medium1100.0 / 10022/22OK42.6s570 / 1.2k
CG-AL-M006medium1100.0 / 10018/18OK1m 5s435 / 1.3k
CG-AL-M007medium20.0 / 1000/0FAIL35.5s2.3k / 2.3k
CG-AL-M008medium262.5 / 10010/12OK1m 40s5.0k / 5.4k
CG-AL-M009medium1100.0 / 10011/11OK36.1s439 / 1.3k
CG-AL-M010medium1100.0 / 10021/21OK3m 22s646 / 1.8k
CG-AL-M020medium1100.0 / 10017/17OK39.9s581 / 698
CG-AL-M021medium1100.0 / 10011/11OK28.0s560 / 500
CG-AL-M022medium1100.0 / 1009/9OK31.6s524 / 611
CG-AL-M023medium262.5 / 10010/11OK3m 32s1.8k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK34.0s511 / 1.0k
CG-AL-M025medium2100.0 / 1007/7OK1m 10s3.0k / 719
CG-AL-M026medium1100.0 / 1008/8OK6m 42s383 / 372
CG-AL-M027medium1100.0 / 10018/18OK1m 0s747 / 1.6k
CG-AL-M028medium2100.0 / 1003/3OK2m 46s1.1k / 526
CG-AL-M029medium20.0 / 1000/0FAIL31.7s936 / 216
CG-AL-M031medium20.0 / 1000/0FAIL37.1s2.9k / 1.5k
CG-AL-M032medium1100.0 / 1003/3OK37.7s510 / 192
CG-AL-M033medium1100.0 / 1002/2OK46.5s449 / 236
CG-AL-M034medium20.0 / 1000/0FAIL1m 19s1.8k / 407
CG-AL-M035medium1100.0 / 1002/2OK26.7s328 / 87
CG-AL-M036medium20.0 / 1000/0FAIL6m 26s1.6k / 634
CG-AL-M037medium2100.0 / 1002/2OK6m 13s1.4k / 470
CG-AL-M038medium1100.0 / 1002/2OK2m 47s399 / 161
CG-AL-M039medium1100.0 / 1002/2OK3m 37s468 / 345
CG-AL-M040medium20.0 / 1000/0FAIL6m 44s1.1k / 316
CG-AL-M041medium1100.0 / 1003/3OK8m 44s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK5m 9s520 / 248
CG-AL-M043medium1100.0 / 1005/5OK5m 0s472 / 320
CG-AL-M044medium1100.0 / 1006/6OK3m 23s654 / 530
CG-AL-M045medium1100.0 / 1006/6OK34.1s729 / 136
CG-AL-M088medium1100.0 / 1006/6OK30.1s407 / 408
CG-AL-M112medium1100.0 / 1004/4OK27.4s581 / 671