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.

84.5% 93/110 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.

70.8 / 100
Cost $4.16
Tokens 136k / 139k input / output, all attempts
Duration 1h 34m
Filter:
Per-task results for run f14a129e-6669-4fbd-a962-68896bcada4c
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK42.6s927 / 570
CG-AL-E002easy1100.0 / 1006/6OK3m 9s285 / 297
CG-AL-E003easy1100.0 / 1005/5OK50.2s273 / 129
CG-AL-E004easy1100.0 / 1006/6OK48.1s300 / 247
CG-AL-E005easy1100.0 / 10013/13OK45.4s315 / 597
CG-AL-E006easy1100.0 / 1007/7OK3m 41s301 / 422
CG-AL-E007easy1100.0 / 1007/7OK55.3s371 / 165
CG-AL-E008easy1100.0 / 1006/6OK58.4s291 / 350
CG-AL-E009easy1100.0 / 1005/5OK1m 2s285 / 207
CG-AL-E010easy1100.0 / 1005/5OK1m 5s296 / 132
CG-AL-E031easy1100.0 / 1003/3OK1m 6s428 / 404
CG-AL-E032easy1100.0 / 1001/1OK1m 1s239 / 56
CG-AL-E045easy1100.0 / 1004/4OK23.8s385 / 339
CG-AL-E050easy1100.0 / 10013/13OK30.3s415 / 759
CG-AL-E051easy1100.0 / 10015/15OK30.8s520 / 798
CG-AL-E052easy2100.0 / 10016/16OK23.8s1.6k / 493
CG-AL-E053easy1100.0 / 1003/3OK3m 10s312 / 166
CG-AL-E054easy1100.0 / 1009/9OK21.8s426 / 316
CG-AL-E055easy1100.0 / 1008/8OK22.3s385 / 216
CG-AL-E056easy262.5 / 10013/15OK22.2s2.0k / 725
CG-AL-E057easy20.0 / 1000/0FAIL10.7s1.6k / 772
CG-AL-E058easy1100.0 / 1001/1OK21.0s414 / 117
CG-AL-H001hard1100.0 / 10025/25OK23.3s491 / 394
CG-AL-H002hard1100.0 / 1004/4OK24.0s496 / 579
CG-AL-H003hard1100.0 / 1005/5OK26.3s524 / 673
CG-AL-H004hard1100.0 / 10014/14OK24.4s535 / 495
CG-AL-H005hard1100.0 / 1006/6OK29.8s802 / 700
CG-AL-H006hard1100.0 / 1006/6OK22.1s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK25.4s625 / 680
CG-AL-H008hard1100.0 / 10010/10OK23.7s588 / 423
CG-AL-H009hard1100.0 / 10011/11OK28.8s688 / 813
CG-AL-H010hard1100.0 / 1008/8OK27.2s561 / 407
CG-AL-H011hard20.0 / 1000/0FAIL9.0s1.1k / 401
CG-AL-H013hard1100.0 / 1009/9OK24.3s392 / 323
CG-AL-H014hard2100.0 / 1007/7OK22.2s1.8k / 1.3k
CG-AL-H015hard1100.0 / 1004/4OK20.4s443 / 325
CG-AL-H016hard1100.0 / 1004/4OK21.6s446 / 313
CG-AL-H017hard2100.0 / 1003/3OK19.8s1.1k / 581
CG-AL-H018hard1100.0 / 1006/6OK24.9s462 / 537
CG-AL-H019hard1100.0 / 1005/5OK19.9s349 / 194
CG-AL-H020hard2100.0 / 10010/10OK25.4s2.5k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL14.3s2.6k / 1.5k
CG-AL-H022hard1100.0 / 10021/21OK27.8s826 / 1.1k
CG-AL-H023hard20.0 / 1000/0FAIL2m 48s20k / 26k
CG-AL-H024hard1100.0 / 1009/9OK48.3s573 / 937
CG-AL-H025hard1100.0 / 1007/7OK22.0s388 / 207
CG-AL-H026hard1100.0 / 1008/8OK20.8s509 / 367
CG-AL-H027hard1100.0 / 1004/4OK20.9s827 / 227
CG-AL-H028hard2100.0 / 1009/9OK23.4s2.7k / 1.9k
CG-AL-H029hard262.5 / 10016/18OK26.0s3.2k / 2.6k
CG-AL-H030hard1100.0 / 10010/10OK23.3s747 / 732
CG-AL-H031hard1100.0 / 10022/22OK27.0s1.1k / 1.2k
CG-AL-H032hard1100.0 / 10019/19OK28.2s824 / 1.1k
CG-AL-H033hard1100.0 / 1005/5OK2m 53s823 / 1.7k
CG-AL-H034hard2100.0 / 1003/3OK17.0s1.5k / 350
CG-AL-H035hard1100.0 / 1003/3OK17.1s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK19.1s419 / 221
CG-AL-H037hard1100.0 / 1003/3OK21.6s546 / 446
CG-AL-H038hard1100.0 / 1003/3OK18.5s610 / 241
CG-AL-H039hard1100.0 / 1004/4OK21.1s524 / 258
CG-AL-H040hard1100.0 / 1002/2OK18.0s430 / 184
CG-AL-H041hard1100.0 / 1003/3OK23.1s662 / 549
CG-AL-H042hard1100.0 / 1003/3OK19.4s434 / 155
CG-AL-H043hard1100.0 / 1005/5OK16.5s430 / 98
CG-AL-H050hard262.5 / 1002/3OK23.5s1.3k / 1.5k
CG-AL-H051hard1100.0 / 1004/4OK18.2s695 / 137
CG-AL-H052hard1100.0 / 1005/5OK17.6s784 / 120
CG-AL-H053hard1100.0 / 1004/4OK18.4s598 / 256
CG-AL-H054hard2100.0 / 1005/5OK22.7s2.5k / 1.4k
CG-AL-H056hard2100.0 / 1004/4OK26.8s1.7k / 988
CG-AL-H057hard1100.0 / 1004/4OK2m 33s776 / 360
CG-AL-H058hard1100.0 / 1005/5OK22.2s644 / 326
CG-AL-H205hard1100.0 / 1006/6OK21.0s535 / 477
CG-AL-M001medium20.0 / 1000/0FAIL9.2s1.6k / 961
CG-AL-M002medium1100.0 / 10022/22OK21.3s471 / 506
CG-AL-M003medium2100.0 / 1009/9OK23.6s2.0k / 1.8k
CG-AL-M004medium1100.0 / 10012/12OK2m 57s496 / 1.3k
CG-AL-M005medium2100.0 / 10022/22OK34.2s4.2k / 4.6k
CG-AL-M006medium1100.0 / 10018/18OK37.8s445 / 1.7k
CG-AL-M007medium20.0 / 1000/0FAIL2m 1s2.6k / 5.9k
CG-AL-M008medium20.0 / 1000/0FAIL1m 53s5.6k / 14k
CG-AL-M009medium20.0 / 1000/0FAIL2m 38s12k / 21k
CG-AL-M010medium1100.0 / 10021/21OK3m 2s661 / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK21.6s2.2k / 1.6k
CG-AL-M021medium1100.0 / 10011/11OK22.7s595 / 593
CG-AL-M022medium1100.0 / 1009/9OK23.5s554 / 664
CG-AL-M023medium262.5 / 10010/11OK20.2s1.9k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK27.4s518 / 1.2k
CG-AL-M025medium1100.0 / 1007/7OK18.4s457 / 365
CG-AL-M026medium1100.0 / 1008/8OK20.5s426 / 408
CG-AL-M027medium2100.0 / 10018/18OK26.8s4.0k / 3.0k
CG-AL-M028medium2100.0 / 1003/3OK2m 36s1.2k / 649
CG-AL-M029medium2100.0 / 1003/3OK2m 35s1.0k / 233
CG-AL-M031medium20.0 / 1000/0FAIL12.6s3.3k / 1.9k
CG-AL-M032medium1100.0 / 1003/3OK18.5s549 / 240
CG-AL-M033medium1100.0 / 1002/2OK18.1s492 / 284
CG-AL-M034medium262.5 / 1000/2OK18.6s1.9k / 545
CG-AL-M035medium1100.0 / 1002/2OK21.6s358 / 98
CG-AL-M036medium20.0 / 1000/0FAIL9.1s1.8k / 703
CG-AL-M037medium20.0 / 1000/0FAIL8.3s1.5k / 506
CG-AL-M038medium1100.0 / 1002/2OK19.1s433 / 180
CG-AL-M039medium1100.0 / 1002/2OK2m 35s502 / 458
CG-AL-M040medium20.0 / 1000/0FAIL8.6s883 / 313
CG-AL-M041medium1100.0 / 1003/3OK15.5s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK18.1s538 / 291
CG-AL-M043medium1100.0 / 1005/5OK19.6s483 / 382
CG-AL-M044medium1100.0 / 1006/6OK2m 31s719 / 677
CG-AL-M045medium1100.0 / 1006/6OK17.5s776 / 183
CG-AL-M088medium1100.0 / 1006/6OK19.6s451 / 476
CG-AL-M112medium1100.0 / 1004/4OK22.3s620 / 736