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.

52.6 / 100
Cost $1.12
Tokens 257k / 82k input / output, all attempts
Duration 1h 36m
Filter:
Per-task results for run 90a07673-dba9-4713-971c-01581e2fdaac
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK18.6s265 / 228
CG-AL-E002easy1100.0 / 1006/6OK2m 35s278 / 242
CG-AL-E003easy1100.0 / 1005/5OK22.4s263 / 114
CG-AL-E004easy1100.0 / 1006/6OK34.0s288 / 229
CG-AL-E005easy1100.0 / 10013/13OK30.7s299 / 243
CG-AL-E006easy2100.0 / 1007/7OK2m 38s2.0k / 613
CG-AL-E007easy1100.0 / 1007/7OK37.9s348 / 163
CG-AL-E008easy1100.0 / 1006/6OK46.9s271 / 258
CG-AL-E009easy1100.0 / 1005/5OK42.7s274 / 190
CG-AL-E010easy1100.0 / 1005/5OK47.4s278 / 148
CG-AL-E031easy1100.0 / 1003/3OK50.9s408 / 470
CG-AL-E032easy1100.0 / 1001/1OK42.5s222 / 47
CG-AL-E045easy1100.0 / 1004/4OK21.6s362 / 342
CG-AL-E050easy20.0 / 1000/0FAIL15.9s2.1k / 399
CG-AL-E051easy2100.0 / 10015/15OK25.0s3.8k / 1.7k
CG-AL-E052easy2100.0 / 10016/16OK30.2s1.6k / 494
CG-AL-E053easy1100.0 / 1003/3OK2m 21s303 / 141
CG-AL-E054easy1100.0 / 1009/9OK25.3s404 / 194
CG-AL-E055easy1100.0 / 1008/8OK21.5s344 / 233
CG-AL-E056easy2100.0 / 10015/15OK22.9s1.9k / 701
CG-AL-E057easy20.0 / 1000/0FAIL1m 7s4.9k / 976
CG-AL-E058easy2100.0 / 1001/1OK45.2s1.7k / 363
CG-AL-H001hard1100.0 / 10025/25OK20.4s470 / 304
CG-AL-H002hard1100.0 / 1004/4OK19.6s448 / 558
CG-AL-H003hard1100.0 / 1005/5OK22.4s491 / 712
CG-AL-H004hard1100.0 / 10014/14OK19.7s502 / 408
CG-AL-H005hard1100.0 / 1006/6OK26.5s724 / 981
CG-AL-H006hard1100.0 / 1006/6OK20.2s420 / 236
CG-AL-H007hard1100.0 / 10010/10OK27.8s558 / 599
CG-AL-H008hard2100.0 / 10010/10OK18.9s1.6k / 722
CG-AL-H009hard1100.0 / 10011/11OK22.8s600 / 576
CG-AL-H010hard1100.0 / 1008/8OK27.0s522 / 366
CG-AL-H011hard2100.0 / 1005/5OK18.1s988 / 418
CG-AL-H013hard1100.0 / 1009/9OK21.0s371 / 307
CG-AL-H014hard20.0 / 1000/0FAIL13.6s1.4k / 783
CG-AL-H015hard1100.0 / 1004/4OK17.5s408 / 293
CG-AL-H016hard1100.0 / 1004/4OK19.8s407 / 259
CG-AL-H017hard2100.0 / 1003/3OK20.0s1.0k / 531
CG-AL-H018hard2100.0 / 1006/6OK28.7s2.3k / 1.2k
CG-AL-H019hard2100.0 / 1005/5OK16.8s877 / 329
CG-AL-H020hard20.0 / 1000/0FAIL1m 12s6.7k / 2.1k
CG-AL-H021hard2100.0 / 10020/20OK37.7s17k / 1.4k
CG-AL-H022hard20.0 / 1000/0FAIL19.7s3.7k / 1.8k
CG-AL-H023hard20.0 / 1000/0FAIL1m 11s14k / 1.8k
CG-AL-H024hard1100.0 / 1009/9OK27.5s529 / 988
CG-AL-H025hard1100.0 / 1007/7OK18.8s372 / 280
CG-AL-H026hard1100.0 / 1008/8OK21.2s467 / 305
CG-AL-H027hard1100.0 / 1004/4OK46.8s1.8k / 368
CG-AL-H028hard1100.0 / 1009/9OK27.9s647 / 486
CG-AL-H029hard20.0 / 1000/0FAIL37.2s6.1k / 992
CG-AL-H030hard20.0 / 1000/0FAIL39.4s8.6k / 2.2k
CG-AL-H031hard20.0 / 1000/0FAIL1m 8s16k / 2.3k
CG-AL-H032hard2100.0 / 10019/19OK24.6s2.5k / 1.9k
CG-AL-H033hard20.0 / 1000/0FAIL1m 8s11k / 5.7k
CG-AL-H034hard262.5 / 1002/3OK25.3s2.6k / 552
CG-AL-H035hard1100.0 / 1003/3OK18.4s300 / 97
CG-AL-H036hard2100.0 / 1005/5OK25.3s1.0k / 355
CG-AL-H037hard2100.0 / 1003/3OK21.8s1.3k / 422
CG-AL-H038hard1100.0 / 1003/3OK25.6s580 / 235
CG-AL-H039hard1100.0 / 1004/4OK17.8s489 / 254
CG-AL-H040hard1100.0 / 1002/2OK18.1s403 / 160
CG-AL-H041hard1100.0 / 1003/3OK29.2s620 / 412
CG-AL-H042hard2100.0 / 1003/3OK17.3s953 / 202
CG-AL-H043hard1100.0 / 1005/5OK16.8s399 / 90
CG-AL-H050hard2100.0 / 1003/3OK25.0s1.5k / 340
CG-AL-H051hard1100.0 / 1004/4OK29.9s664 / 163
CG-AL-H052hard1100.0 / 1005/5OK29.2s726 / 104
CG-AL-H053hard1100.0 / 1004/4OK17.9s570 / 241
CG-AL-H054hard20.0 / 1000/0FAIL14.9s2.0k / 648
CG-AL-H056hard20.0 / 1000/0FAIL9.7s1.6k / 314
CG-AL-H057hard1100.0 / 1004/4OK2m 42s728 / 269
CG-AL-H058hard1100.0 / 1005/5OK30.5s604 / 300
CG-AL-H205hard1100.0 / 1006/6OK20.2s447 / 415
CG-AL-M001medium20.0 / 1000/0FAIL11.2s1.5k / 838
CG-AL-M002medium20.0 / 1000/0FAIL1m 20s6.9k / 1.1k
CG-AL-M003medium20.0 / 1000/0FAIL22.0s2.7k / 1.3k
CG-AL-M004medium1100.0 / 10012/12OK2m 55s456 / 1.2k
CG-AL-M005medium20.0 / 1000/0FAIL52.5s4.3k / 1.8k
CG-AL-M006medium20.0 / 1000/0FAIL1m 12s8.6k / 3.4k
CG-AL-M007medium20.0 / 1000/0FAIL50.5s4.4k / 981
CG-AL-M008medium20.0 / 1000/0FAIL1m 22s12k / 1.3k
CG-AL-M009medium20.0 / 1000/0FAIL31.2s5.4k / 1.7k
CG-AL-M010medium20.0 / 1000/0FAIL1m 12s14k / 4.3k
CG-AL-M020medium2100.0 / 10017/17OK48.4s4.1k / 1.6k
CG-AL-M021medium1100.0 / 10011/11OK21.0s560 / 506
CG-AL-M022medium1100.0 / 1009/9OK25.3s524 / 627
CG-AL-M023medium20.0 / 1000/0FAIL1m 23s6.5k / 1.2k
CG-AL-M024medium2100.0 / 10010/10OK24.5s2.7k / 1.4k
CG-AL-M025medium1100.0 / 1007/7OK21.6s421 / 363
CG-AL-M026medium262.5 / 1006/8OK28.1s1.1k / 565
CG-AL-M027medium20.0 / 1000/0FAIL1m 13s15k / 2.3k
CG-AL-M028medium20.0 / 1000/0FAIL16.3s1.1k / 534
CG-AL-M029medium2100.0 / 1003/3OK2m 37s930 / 196
CG-AL-M031medium20.0 / 1000/0FAIL18.8s2.8k / 1.5k
CG-AL-M032medium1100.0 / 1003/3OK20.6s510 / 186
CG-AL-M033medium1100.0 / 1002/2OK19.4s449 / 244
CG-AL-M034medium262.5 / 1001/2OK30.5s1.6k / 484
CG-AL-M035medium1100.0 / 1002/2OK17.4s328 / 90
CG-AL-M036medium20.0 / 1000/0FAIL46.9s4.1k / 1.0k
CG-AL-M037medium20.0 / 1000/0FAIL34.5s2.5k / 454
CG-AL-M038medium1100.0 / 1002/2OK19.7s399 / 171
CG-AL-M039medium1100.0 / 1002/2OK2m 24s468 / 353
CG-AL-M040medium262.5 / 1001/2OK27.2s849 / 321
CG-AL-M041medium1100.0 / 1003/3OK16.1s330 / 108
CG-AL-M042medium1100.0 / 1008/8OK21.4s520 / 289
CG-AL-M043medium1100.0 / 1005/5OK25.9s472 / 219
CG-AL-M044medium1100.0 / 1006/6OK2m 22s654 / 532
CG-AL-M045medium1100.0 / 1006/6OK19.5s729 / 136
CG-AL-M088medium1100.0 / 1006/6OK19.9s407 / 417
CG-AL-M112medium2100.0 / 1004/4OK22.5s2.9k / 1.4k