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.

71.8% 79/110 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.

53.6 / 100
Cost $1.09
Tokens 249k / 80k input / output, all attempts
Duration 1h 37m
Filter:
Per-task results for run 2c01b44c-9f4a-4308-ba37-85444d3d3796
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK19.3s265 / 228
CG-AL-E002easy1100.0 / 1006/6OK2m 21s278 / 247
CG-AL-E003easy1100.0 / 1005/5OK22.3s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK25.7s288 / 229
CG-AL-E005easy1100.0 / 10013/13OK29.7s299 / 249
CG-AL-E006easy2100.0 / 1007/7OK2m 39s2.0k / 602
CG-AL-E007easy1100.0 / 1007/7OK34.7s348 / 163
CG-AL-E008easy1100.0 / 1006/6OK43.4s271 / 283
CG-AL-E009easy2100.0 / 1005/5OK30.7s889 / 396
CG-AL-E010easy1100.0 / 1005/5OK45.9s278 / 133
CG-AL-E031easy1100.0 / 1003/3OK46.3s408 / 466
CG-AL-E032easy1100.0 / 1001/1OK42.1s222 / 157
CG-AL-E045easy1100.0 / 1004/4OK23.6s362 / 346
CG-AL-E050easy20.0 / 1000/0FAIL14.4s2.1k / 399
CG-AL-E051easy20.0 / 1000/0FAIL1m 13s8.3k / 2.1k
CG-AL-E052easy2100.0 / 10016/16OK29.7s1.6k / 470
CG-AL-E053easy1100.0 / 1003/3OK2m 38s303 / 141
CG-AL-E054easy1100.0 / 1009/9OK25.4s404 / 177
CG-AL-E055easy1100.0 / 1008/8OK20.1s344 / 204
CG-AL-E056easy2100.0 / 10015/15OK20.4s1.9k / 665
CG-AL-E057easy20.0 / 1000/0FAIL41.4s2.6k / 842
CG-AL-E058easy20.0 / 1000/0FAIL25.0s1.6k / 312
CG-AL-H001hard1100.0 / 10025/25OK20.4s470 / 324
CG-AL-H002hard1100.0 / 1004/4OK20.3s448 / 559
CG-AL-H003hard1100.0 / 1005/5OK26.3s491 / 712
CG-AL-H004hard1100.0 / 10014/14OK19.6s502 / 408
CG-AL-H005hard1100.0 / 1006/6OK27.1s724 / 544
CG-AL-H006hard1100.0 / 1006/6OK18.6s420 / 225
CG-AL-H007hard1100.0 / 10010/10OK21.4s558 / 529
CG-AL-H008hard1100.0 / 10010/10OK22.6s516 / 345
CG-AL-H009hard2100.0 / 10011/11OK27.0s3.1k / 1.4k
CG-AL-H010hard1100.0 / 1008/8OK23.1s522 / 364
CG-AL-H011hard2100.0 / 1005/5OK24.6s986 / 418
CG-AL-H013hard1100.0 / 1009/9OK19.6s371 / 310
CG-AL-H014hard20.0 / 1000/0FAIL17.2s1.5k / 945
CG-AL-H015hard1100.0 / 1004/4OK18.5s408 / 293
CG-AL-H016hard1100.0 / 1004/4OK21.2s407 / 254
CG-AL-H017hard2100.0 / 1003/3OK31.6s1.0k / 529
CG-AL-H018hard1100.0 / 1006/6OK21.5s424 / 498
CG-AL-H019hard1100.0 / 1005/5OK19.9s318 / 166
CG-AL-H020hard20.0 / 1000/0FAIL1m 17s8.3k / 2.1k
CG-AL-H021hard2100.0 / 10020/20OK35.8s17k / 1.3k
CG-AL-H022hard20.0 / 1000/0FAIL49.6s8.2k / 2.9k
CG-AL-H023hard20.0 / 1000/0FAIL57.1s14k / 954
CG-AL-H024hard2100.0 / 1009/9OK30.2s2.7k / 1.5k
CG-AL-H025hard1100.0 / 1007/7OK19.7s372 / 283
CG-AL-H026hard1100.0 / 1008/8OK23.4s467 / 270
CG-AL-H027hard1100.0 / 1004/4OK28.0s785 / 188
CG-AL-H028hard1100.0 / 1009/9OK24.6s647 / 486
CG-AL-H029hard20.0 / 1000/0FAIL1m 18s6.4k / 801
CG-AL-H030hard20.0 / 1000/0FAIL1m 39s7.6k / 1.3k
CG-AL-H031hard20.0 / 1000/0FAIL30.4s5.0k / 2.2k
CG-AL-H032hard2100.0 / 10019/19OK25.3s3.9k / 1.9k
CG-AL-H033hard20.0 / 1000/0FAIL1m 13s9.6k / 5.1k
CG-AL-H034hard20.0 / 1000/0FAIL1m 26s4.8k / 1.0k
CG-AL-H035hard1100.0 / 1003/3OK18.1s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK28.4s995 / 323
CG-AL-H037hard1100.0 / 1003/3OK29.3s514 / 192
CG-AL-H038hard1100.0 / 1003/3OK26.5s580 / 228
CG-AL-H039hard1100.0 / 1004/4OK20.8s489 / 250
CG-AL-H040hard1100.0 / 1002/2OK19.2s403 / 154
CG-AL-H041hard1100.0 / 1003/3OK26.2s620 / 445
CG-AL-H042hard2100.0 / 1003/3OK20.8s951 / 202
CG-AL-H043hard1100.0 / 1005/5OK18.4s399 / 90
CG-AL-H050hard262.5 / 1002/3OK32.0s1.6k / 398
CG-AL-H051hard1100.0 / 1004/4OK52.6s1.5k / 321
CG-AL-H052hard1100.0 / 1005/5OK28.9s726 / 104
CG-AL-H053hard1100.0 / 1004/4OK22.3s570 / 236
CG-AL-H054hard20.0 / 1000/0FAIL12.2s2.0k / 648
CG-AL-H056hard20.0 / 1000/0FAIL9.3s1.6k / 314
CG-AL-H057hard1100.0 / 1004/4OK2m 31s728 / 269
CG-AL-H058hard1100.0 / 1005/5OK31.7s604 / 335
CG-AL-H205hard1100.0 / 1006/6OK20.9s447 / 392
CG-AL-M001medium20.0 / 1000/0FAIL12.8s1.5k / 854
CG-AL-M002medium2100.0 / 10022/22OK18.9s1.4k / 992
CG-AL-M003medium20.0 / 1000/0FAIL1m 17s8.4k / 3.0k
CG-AL-M004medium2100.0 / 10012/12OK3m 3s2.5k / 2.4k
CG-AL-M005medium1100.0 / 10022/22OK32.1s570 / 1.3k
CG-AL-M006medium20.0 / 1000/0FAIL1m 18s8.6k / 2.0k
CG-AL-M007medium20.0 / 1000/0FAIL1m 22s9.6k / 1.8k
CG-AL-M008medium20.0 / 1000/0FAIL1m 24s12k / 1.3k
CG-AL-M009medium2100.0 / 10011/11OK30.8s2.8k / 2.4k
CG-AL-M010medium20.0 / 1000/0FAIL1m 18s13k / 3.6k
CG-AL-M020medium2100.0 / 10017/17OK30.3s2.1k / 1.5k
CG-AL-M021medium1100.0 / 10011/11OK23.9s560 / 490
CG-AL-M022medium1100.0 / 1009/9OK24.0s524 / 626
CG-AL-M023medium20.0 / 1000/0FAIL1m 33s6.5k / 1.2k
CG-AL-M024medium1100.0 / 10010/10OK25.7s511 / 917
CG-AL-M025medium1100.0 / 1007/7OK22.2s421 / 413
CG-AL-M026medium1100.0 / 1008/8OK22.8s383 / 314
CG-AL-M027medium20.0 / 1000/0FAIL1m 18s14k / 1.7k
CG-AL-M028medium20.0 / 1000/0FAIL14.3s1.1k / 549
CG-AL-M029medium20.0 / 1000/0FAIL12.7s936 / 216
CG-AL-M031medium20.0 / 1000/0FAIL18.8s2.8k / 1.5k
CG-AL-M032medium1100.0 / 1003/3OK21.7s510 / 186
CG-AL-M033medium1100.0 / 1002/2OK22.5s449 / 236
CG-AL-M034medium262.5 / 1001/2OK28.5s1.8k / 634
CG-AL-M035medium1100.0 / 1002/2OK18.1s328 / 90
CG-AL-M036medium20.0 / 1000/0FAIL16.6s1.6k / 564
CG-AL-M037medium20.0 / 1000/0FAIL39.5s2.5k / 579
CG-AL-M038medium1100.0 / 1002/2OK19.2s399 / 165
CG-AL-M039medium1100.0 / 1002/2OK2m 30s468 / 359
CG-AL-M040medium262.5 / 1001/2OK22.9s851 / 321
CG-AL-M041medium1100.0 / 1003/3OK17.0s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK22.2s520 / 276
CG-AL-M043medium2100.0 / 1005/5OK24.6s2.3k / 529
CG-AL-M044medium1100.0 / 1006/6OK3m 0s654 / 511
CG-AL-M045medium1100.0 / 1006/6OK23.9s729 / 130
CG-AL-M088medium1100.0 / 1006/6OK22.3s407 / 423
CG-AL-M112medium1100.0 / 1004/4OK26.6s581 / 708