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.

65.5% 72/110 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.

47.0 / 100
Cost $1.16
Tokens 297k / 80k input / output, all attempts
Duration 1h 44m
Filter:
Per-task results for run c574b74f-cca1-4101-8d57-6c03fe99b514
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK28.4s265 / 196
CG-AL-E002easy1100.0 / 1006/6OK3m 3s278 / 246
CG-AL-E003easy1100.0 / 1005/5OK46.9s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK37.9s288 / 229
CG-AL-E005easy1100.0 / 10013/13OK37.5s299 / 240
CG-AL-E006easy2100.0 / 1007/7OK2m 49s2.0k / 585
CG-AL-E007easy1100.0 / 1007/7OK44.4s348 / 163
CG-AL-E008easy1100.0 / 1006/6OK48.0s271 / 290
CG-AL-E009easy1100.0 / 1005/5OK46.2s274 / 190
CG-AL-E010easy1100.0 / 1005/5OK52.0s278 / 133
CG-AL-E031easy1100.0 / 1003/3OK49.6s408 / 466
CG-AL-E032easy1100.0 / 1001/1OK45.1s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK25.1s362 / 342
CG-AL-E050easy20.0 / 1000/0FAIL38.7s4.0k / 441
CG-AL-E051easy20.0 / 1000/0FAIL55.0s6.5k / 2.9k
CG-AL-E052easy2100.0 / 10016/16OK28.9s1.6k / 494
CG-AL-E053easy1100.0 / 1003/3OK2m 29s303 / 141
CG-AL-E054easy20.0 / 1000/0FAIL9.7s1.1k / 410
CG-AL-E055easy1100.0 / 1008/8OK25.0s344 / 227
CG-AL-E056easy2100.0 / 10015/15OK23.6s1.9k / 701
CG-AL-E057easy20.0 / 1000/0FAIL35.5s2.6k / 843
CG-AL-E058easy20.0 / 1000/0FAIL36.5s1.6k / 360
CG-AL-H001hard1100.0 / 10025/25OK20.9s470 / 324
CG-AL-H002hard1100.0 / 1004/4OK21.3s448 / 558
CG-AL-H003hard1100.0 / 1005/5OK25.1s491 / 706
CG-AL-H004hard2100.0 / 10014/14OK20.5s1.5k / 849
CG-AL-H005hard2100.0 / 1006/6OK22.9s3.2k / 1.1k
CG-AL-H006hard1100.0 / 1006/6OK19.2s420 / 225
CG-AL-H007hard1100.0 / 10010/10OK22.8s558 / 583
CG-AL-H008hard1100.0 / 10010/10OK21.1s516 / 349
CG-AL-H009hard2100.0 / 10011/11OK27.3s2.7k / 1.2k
CG-AL-H010hard20.0 / 1000/0FAIL54.0s4.7k / 1.1k
CG-AL-H011hard2100.0 / 1005/5OK23.0s987 / 418
CG-AL-H013hard1100.0 / 1009/9OK19.9s371 / 307
CG-AL-H014hard20.0 / 1000/0FAIL13.8s1.4k / 759
CG-AL-H015hard1100.0 / 1004/4OK18.5s408 / 263
CG-AL-H016hard1100.0 / 1004/4OK19.0s407 / 274
CG-AL-H017hard2100.0 / 1003/3OK29.4s1.0k / 529
CG-AL-H018hard1100.0 / 1006/6OK21.9s424 / 473
CG-AL-H019hard2100.0 / 1005/5OK17.4s868 / 311
CG-AL-H020hard20.0 / 1000/0FAIL1m 16s8.2k / 1.7k
CG-AL-H021hard2100.0 / 10020/20OK33.6s17k / 1.3k
CG-AL-H022hard20.0 / 1000/0FAIL1m 11s12k / 2.0k
CG-AL-H023hard20.0 / 1000/0FAIL1m 10s13k / 1.5k
CG-AL-H024hard1100.0 / 1009/9OK26.9s529 / 720
CG-AL-H025hard1100.0 / 1007/7OK32.5s372 / 196
CG-AL-H026hard1100.0 / 1008/8OK21.8s467 / 307
CG-AL-H027hard20.0 / 1000/0FAIL18.2s2.4k / 172
CG-AL-H028hard1100.0 / 1009/9OK24.4s647 / 486
CG-AL-H029hard20.0 / 1000/0FAIL1m 13s13k / 2.0k
CG-AL-H030hard20.0 / 1000/0FAIL1m 14s9.2k / 1.8k
CG-AL-H031hard20.0 / 1000/0FAIL1m 5s14k / 3.0k
CG-AL-H032hard1100.0 / 10019/19OK38.9s749 / 944
CG-AL-H033hard20.0 / 1000/0FAIL51.8s9.0k / 3.1k
CG-AL-H034hard2100.0 / 1003/3OK28.6s1.5k / 385
CG-AL-H035hard1100.0 / 1003/3OK19.8s300 / 123
CG-AL-H036hard2100.0 / 1005/5OK28.5s996 / 323
CG-AL-H037hard1100.0 / 1003/3OK22.4s514 / 191
CG-AL-H038hard1100.0 / 1003/3OK23.4s580 / 228
CG-AL-H039hard1100.0 / 1004/4OK19.3s489 / 202
CG-AL-H040hard1100.0 / 1002/2OK19.1s403 / 160
CG-AL-H041hard2100.0 / 1003/3OK24.2s3.3k / 860
CG-AL-H042hard2100.0 / 1003/3OK17.9s952 / 202
CG-AL-H043hard1100.0 / 1005/5OK16.9s399 / 90
CG-AL-H050hard262.5 / 1002/3OK18.8s1.3k / 322
CG-AL-H051hard20.0 / 1000/0FAIL39.3s7.2k / 776
CG-AL-H052hard1100.0 / 1005/5OK41.8s1.7k / 264
CG-AL-H053hard1100.0 / 1004/4OK34.9s570 / 241
CG-AL-H054hard20.0 / 1000/0FAIL13.2s2.0k / 600
CG-AL-H056hard20.0 / 1000/0FAIL9.1s1.6k / 314
CG-AL-H057hard1100.0 / 1004/4OK2m 23s728 / 277
CG-AL-H058hard2100.0 / 1005/5OK22.2s2.7k / 695
CG-AL-H205hard1100.0 / 1006/6OK20.4s447 / 415
CG-AL-M001medium20.0 / 1000/0FAIL11.6s1.5k / 854
CG-AL-M002medium20.0 / 1000/0FAIL1m 24s6.9k / 1.2k
CG-AL-M003medium20.0 / 1000/0FAIL1m 25s6.9k / 1.3k
CG-AL-M004medium20.0 / 1000/0FAIL39.5s4.2k / 3.5k
CG-AL-M005medium20.0 / 1000/0FAIL1m 18s9.1k / 2.5k
CG-AL-M006medium20.0 / 1000/0FAIL1m 23s5.9k / 906
CG-AL-M007medium20.0 / 1000/0FAIL1m 31s11k / 1.2k
CG-AL-M008medium20.0 / 1000/0FAIL1m 23s11k / 1.1k
CG-AL-M009medium20.0 / 1000/0FAIL39.0s5.2k / 2.5k
CG-AL-M010medium20.0 / 1000/0FAIL1m 20s9.3k / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK27.0s2.0k / 1.4k
CG-AL-M021medium1100.0 / 10011/11OK22.4s560 / 609
CG-AL-M022medium1100.0 / 1009/9OK27.2s524 / 678
CG-AL-M023medium20.0 / 1000/0FAIL1m 34s6.5k / 1.2k
CG-AL-M024medium1100.0 / 10010/10OK26.6s511 / 786
CG-AL-M025medium1100.0 / 1007/7OK21.1s421 / 351
CG-AL-M026medium1100.0 / 1008/8OK28.0s383 / 341
CG-AL-M027medium20.0 / 1000/0FAIL1m 1s4.7k / 496
CG-AL-M028medium20.0 / 1000/0FAIL18.8s1.1k / 559
CG-AL-M029medium20.0 / 1000/0FAIL13.9s937 / 216
CG-AL-M031medium20.0 / 1000/0FAIL1m 3s8.9k / 2.0k
CG-AL-M032medium1100.0 / 1003/3OK20.9s510 / 192
CG-AL-M033medium1100.0 / 1002/2OK23.4s449 / 240
CG-AL-M034medium20.0 / 1000/0FAIL1m 31s5.1k / 866
CG-AL-M035medium1100.0 / 1002/2OK16.0s328 / 90
CG-AL-M036medium20.0 / 1000/0FAIL53.7s4.1k / 939
CG-AL-M037medium20.0 / 1000/0FAIL1m 10s3.6k / 533
CG-AL-M038medium1100.0 / 1002/2OK21.9s399 / 167
CG-AL-M039medium1100.0 / 1002/2OK2m 40s468 / 352
CG-AL-M040medium20.0 / 1000/0FAIL31.6s1.6k / 401
CG-AL-M041medium1100.0 / 1003/3OK16.9s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK23.4s520 / 308
CG-AL-M043medium1100.0 / 1005/5OK27.7s472 / 261
CG-AL-M044medium1100.0 / 1006/6OK2m 28s654 / 532
CG-AL-M045medium1100.0 / 1006/6OK22.9s729 / 130
CG-AL-M088medium1100.0 / 1006/6OK19.8s407 / 417
CG-AL-M112medium2100.0 / 1004/4OK23.9s2.9k / 1.4k