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.

52.2% 121/232 of 232 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.

57.6 / 100
Cost $3.56
Tokens 972k / 518k input / output, all attempts
Duration 1h 4m
Filter:
Per-task results for run 8c384b82-1d4c-43df-8e2d-2594ce8242fe
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.7s272 / 231
CG-AL-E006easy20.0 / 1000/0FAIL10.5s1.1k / 765
CG-AL-E010easy20.0 / 1000/0FAIL10.6s791 / 246
CG-AL-E050easy20.0 / 1000/0FAIL10.1s2.2k / 451
CG-AL-E052easy1100.0 / 10016/16OK11.9s391 / 282
CG-AL-E054easy20.0 / 1000/0FAIL9.8s1.2k / 490
CG-AL-E056easy262.5 / 10013/15OK12.4s1.7k / 670
CG-AL-H007hard2100.0 / 10011/11OK12.6s2.1k / 1.4k
CG-AL-H011hard20.0 / 1000/0FAIL3.9s1.4k / 437
CG-AL-H014hard20.0 / 1000/0FAIL4.2s1.6k / 916
CG-AL-H017hard20.0 / 1000/0FAIL4.5s1.3k / 631
CG-AL-H020hard20.0 / 1000/0FAIL3.8s2.5k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL4.5s3.0k / 1.7k
CG-AL-H023hard20.0 / 1000/0FAIL4.0s7.7k / 9.0k
CG-AL-H027hard262.5 / 1002/4OK12.3s2.6k / 866
CG-AL-H029hard262.5 / 10016/18OK11.5s3.4k / 2.4k
CG-AL-H030hard262.5 / 1009/10OK11.2s2.3k / 1.3k
CG-AL-H031hard2100.0 / 10022/22OK11.5s3.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK11.1s1.5k / 338
CG-AL-H036hard2100.0 / 1005/5OK11.0s1.3k / 325
CG-AL-H037hard20.0 / 1000/0FAIL4.3s1.6k / 402
CG-AL-H041hard20.0 / 1000/0FAIL4.2s2.2k / 1.2k
CG-AL-H050hard262.5 / 1002/3OK11.2s1.4k / 423
CG-AL-H054hard2100.0 / 1005/5OK10.8s2.7k / 1.9k
CG-AL-H056hard20.0 / 1000/0FAIL4.2s1.7k / 330
CG-AL-M001medium20.0 / 1000/0FAIL4.1s1.9k / 1.1k
CG-AL-M003medium20.0 / 1000/0FAIL4.1s2.0k / 1.9k
CG-AL-M004medium1100.0 / 10012/12OK31.6s496 / 1.1k
CG-AL-M006medium20.0 / 1000/0FAIL4.1s2.1k / 2.3k
CG-AL-M007medium20.0 / 1000/0FAIL4.1s4.0k / 4.7k
CG-AL-M008medium20.0 / 1000/0FAIL4.1s5.8k / 6.8k
CG-AL-M009medium1100.0 / 10011/11OK11.4s475 / 3.5k
CG-AL-M010medium262.5 / 10020/21OK29.7s3.4k / 3.9k
CG-AL-M020medium262.5 / 10015/17OK10.8s3.3k / 2.0k
CG-AL-M023medium1100.0 / 10011/11OK11.4s536 / 541
CG-AL-M025medium262.5 / 1002/8OK10.9s1.4k / 780
CG-AL-M026medium1100.0 / 1008/8OK17.0s426 / 378
CG-AL-M027medium20.0 / 1000/0FAIL4.0s4.5k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK26.5s1.2k / 610
CG-AL-M031medium20.0 / 1000/0FAIL4.0s2.6k / 1.4k
CG-AL-M034medium266.7 / 1000/2OK10.6s1.8k / 375
CG-AL-M036medium211.1 / 1000/0FAIL4.1s1.7k / 607
CG-AL-M040medium2100.0 / 1002/2OK10.7s913 / 347
CG-AL-M042medium2100.0 / 1008/8OK10.7s3.0k / 741
CG-AL-X001hard262.5 / 1001/2OK11.0s1.1k / 176
CG-AL-X002hard1100.0 / 1004/4OK11.8s542 / 408
CG-AL-X003hard262.5 / 1002/3OK10.3s720 / 309
CG-AL-X004medium1100.0 / 1003/3OK11.6s387 / 245
CG-AL-X005hard1100.0 / 1002/2OK11.8s352 / 188
CG-AL-X006hard262.5 / 1002/3OK20.6s1.6k / 777
CG-AL-X007hard1100.0 / 1002/2OK1m 55s400 / 245
CG-AL-X008hard1100.0 / 1001/1OK11.4s449 / 522
CG-AL-X009medium1100.0 / 1002/2OK11.5s334 / 128
CG-AL-X010medium1100.0 / 1003/3OK11.6s306 / 159
CG-AL-X011medium1100.0 / 1002/2OK11.8s396 / 162
CG-AL-X012hard20.0 / 1000/0FAIL3.9s1.8k / 683
CG-AL-X013hard1100.0 / 1002/2OK11.2s286 / 90
CG-AL-X014medium1100.0 / 1004/4OK11.6s313 / 91
CG-AL-X017medium20.0 / 1000/0FAIL0ms1.7k / 64k
CG-AL-X018medium1100.0 / 1003/3OK11.6s420 / 173
CG-AL-X019medium2100.0 / 1003/3OK11.0s2.1k / 377
CG-AL-X022medium2100.0 / 1003/3OK10.8s1.5k / 474
CG-AL-X024medium1100.0 / 1003/3OK11.7s371 / 348
CG-AL-X025medium1100.0 / 1001/1OK11.3s413 / 330
CG-AL-X026medium1100.0 / 1003/3OK11.3s353 / 184
CG-AL-X027medium2100.0 / 1004/4OK10.9s824 / 380
CG-AL-X029medium1100.0 / 1002/2OK11.7s304 / 171
CG-AL-X030medium1100.0 / 1002/2OK11.9s271 / 102
CG-AL-X031medium1100.0 / 1003/3OK11.7s321 / 174
CG-AL-X033hard1100.0 / 1002/2OK12.4s380 / 134
CG-AL-X034hard1100.0 / 1003/3OK12.2s333 / 144
CG-AL-X035hard20.0 / 1000/0FAIL4.3s999 / 438
CG-AL-X037hard20.0 / 1000/0FAIL4.1s1.2k / 515
CG-AL-X040hard20.0 / 1000/0FAIL4.1s1.7k / 867
CG-AL-X041hard20.0 / 1000/0FAIL4.1s1.4k / 738
CG-AL-X043hard20.0 / 1000/0FAIL3.9s1.9k / 1.5k
CG-AL-X044hard262.5 / 1000/3OK10.8s1.2k / 490
CG-AL-X045hard262.5 / 1000/3OK10.9s2.0k / 667
CG-AL-X046hard262.5 / 1000/2OK11.1s1.9k / 574
CG-AL-X047hard20.0 / 1000/0FAIL4.1s2.4k / 1.1k
CG-AL-X050hard262.5 / 1000/2OK10.7s1.9k / 858
CG-AL-X051hard262.5 / 1000/2OK10.9s2.1k / 932
CG-AL-X052hard262.5 / 1000/3OK10.7s2.0k / 510
CG-AL-X055hard1100.0 / 1005/5OK12.8s370 / 318
CG-AL-X056hard1100.0 / 1005/5OK13.3s297 / 157
CG-AL-X057hard1100.0 / 1005/5OK12.3s274 / 125
CG-AL-X058hard1100.0 / 1005/5OK12.8s347 / 262
CG-AL-X059hard1100.0 / 1003/3OK12.2s361 / 83
CG-AL-X060hard2100.0 / 1003/3OK10.7s1.8k / 246
CG-AL-X061hard2100.0 / 1004/4OK10.6s1.5k / 337
CG-AL-X062hard1100.0 / 1004/4OK12.2s411 / 370
CG-AL-X063hard20.0 / 1000/0FAIL4.1s1.1k / 408
CG-AL-X064hard1100.0 / 1007/7OK11.7s300 / 288
CG-AL-X065hard1100.0 / 1006/6OK12.0s868 / 650
CG-AL-X066hard1100.0 / 10014/14OK12.4s1.7k / 1.4k
CG-AL-X067hard262.5 / 1006/7OK10.4s1.9k / 917
CG-AL-X068hard262.5 / 1003/12OK10.8s2.9k / 2.1k
CG-AL-X069hard262.5 / 1000/8OK11.9s3.0k / 1.8k
CG-AL-X070hard1100.0 / 10012/12OK12.3s1.4k / 877
CG-AL-X071hard1100.0 / 1008/8OK12.6s1.7k / 1.4k
CG-AL-X072hard1100.0 / 1007/7OK12.0s1.4k / 1.1k
CG-AL-X073hard1100.0 / 1008/8OK12.0s1.8k / 1.6k
CG-AL-X074hard20.0 / 1000/0FAIL4.1s4.3k / 3.4k
CG-AL-X075hard262.5 / 1000/7OK11.3s4.2k / 1.6k
CG-AL-X076hard2100.0 / 10014/14OK11.2s4.2k / 1.6k
CG-AL-X077hard2100.0 / 10022/22OK10.8s4.4k / 4.2k
CG-AL-X078hard1100.0 / 10017/17OK11.3s1.5k / 1.2k
CG-AL-X079hard262.5 / 1002/11OK10.8s4.0k / 3.1k
CG-AL-X080hard262.5 / 1002/7OK12.2s3.1k / 2.3k
CG-AL-X081hard1100.0 / 1008/8OK11.4s1.1k / 741
CG-AL-X082hard2100.0 / 10015/15OK12.5s3.2k / 2.3k
CG-AL-X083hard1100.0 / 1009/9OK11.4s2.0k / 1.6k
CG-AL-X084hard2100.0 / 10010/10OK12.7s4.1k / 3.0k
CG-AL-X085hard1100.0 / 1007/7OK11.4s1.2k / 789
CG-AL-X086hard20.0 / 1000/0FAIL4.4s4.1k / 3.7k
CG-AL-X087hard1100.0 / 1003/3OK10.8s1.3k / 972
CG-AL-X088hard1100.0 / 1006/6OK11.1s1.2k / 956
CG-AL-X089hard2100.0 / 10011/11OK12.2s3.2k / 2.5k
CG-AL-X090hard262.5 / 1009/10OK12.0s3.3k / 2.0k
CG-AL-X091hard262.5 / 1005/6OK11.8s1.6k / 843
CG-AL-X092hard262.5 / 10012/15OK11.6s2.4k / 864
CG-AL-X093hard2100.0 / 10010/10OK11.9s2.8k / 1.8k
CG-AL-X094hard1100.0 / 1007/7OK11.8s944 / 654
CG-AL-X095hard1100.0 / 1005/5OK12.2s957 / 693
CG-AL-X096hard262.5 / 10029/49OK12.4s9.0k / 8.1k
CG-AL-X097hard2100.0 / 10046/46OK12.2s9.6k / 9.0k
CG-AL-X098hard1100.0 / 10029/29OK12.2s3.4k / 3.0k
CG-AL-X099hard2100.0 / 10039/39OK13.8s10.0k / 9.2k
CG-AL-X100hard1100.0 / 10035/35OK12.1s4.4k / 3.9k
CG-AL-X101hard1100.0 / 10010/10OK12.0s1.3k / 1.0k
CG-AL-X102hard1100.0 / 1008/8OK11.8s615 / 339
CG-AL-X103hard1100.0 / 1007/7OK12.3s891 / 596
CG-AL-X104hard1100.0 / 1006/6OK11.7s1.3k / 1.0k
CG-AL-X105hard1100.0 / 1006/6OK11.2s963 / 601
CG-AL-X106hard1100.0 / 1005/5OK11.0s1.1k / 836
CG-AL-X107hard1100.0 / 1004/4OK11.8s1.0k / 801
CG-AL-X108hard1100.0 / 1006/6OK12.3s865 / 457
CG-AL-X109hard1100.0 / 1005/5OK11.4s638 / 319
CG-AL-X110hard1100.0 / 10017/17OK11.2s1.5k / 1.3k
CG-AL-X111hard20.0 / 1000/0FAIL4.2s3.0k / 2.3k
CG-AL-X112hard262.5 / 10011/12OK12.8s2.8k / 2.0k
CG-AL-X113hard1100.0 / 10013/13OK11.7s897 / 566
CG-AL-X114hard1100.0 / 1007/7OK11.3s909 / 557
CG-AL-X115hard20.0 / 1000/0FAIL4.4s1.7k / 705
CG-AL-X116hard262.5 / 1001/17OK11.7s5.1k / 1.8k
CG-AL-X117hard1100.0 / 1008/8OK11.7s1.2k / 957
CG-AL-X118hard262.5 / 1008/17OK11.8s7.5k / 3.1k
CG-AL-X119hard1100.0 / 10015/15OK11.4s2.1k / 2.0k
CG-AL-X120hard1100.0 / 10012/12OK11.9s1.6k / 1.4k
CG-AL-X121hard1100.0 / 1006/6OK11.3s1.2k / 989
CG-AL-X122hard262.5 / 1009/10OK12.5s4.2k / 3.7k
CG-AL-X123hard20.0 / 1000/0FAIL4.3s1.6k / 680
CG-AL-X124hard1100.0 / 10010/10OK11.5s1.2k / 875
CG-AL-X125hard1100.0 / 1008/8OK12.3s1.7k / 1.4k
CG-AL-X126hard2100.0 / 10014/14OK11.3s4.1k / 1.1k
CG-AL-X127hard1100.0 / 1005/5OK11.4s807 / 489
CG-AL-X128hard1100.0 / 1008/8OK11.4s1.4k / 1.0k
CG-AL-X129hard1100.0 / 10014/14OK11.3s1.5k / 1.3k
CG-AL-X130hard20.0 / 1000/0FAIL4.2s1.4k / 609
CG-AL-X131hard1100.0 / 10013/13OK11.5s1.1k / 737
CG-AL-X132hard1100.0 / 10010/10OK11.4s865 / 548
CG-AL-X133hard262.5 / 1007/8OK12.5s4.2k / 3.3k
CG-AL-X134hard1100.0 / 1006/6OK12.8s1.5k / 1.2k
CG-AL-X135hard1100.0 / 1004/4OK11.1s1.0k / 706
CG-AL-X136hard1100.0 / 1007/7OK11.6s889 / 390
CG-AL-X137hard1100.0 / 1004/4OK11.4s1.1k / 724
CG-AL-X138hard1100.0 / 1009/9OK11.6s1.7k / 1.5k
CG-AL-X139hard1100.0 / 10011/11OK11.9s2.0k / 1.9k
CG-AL-X140hard262.5 / 1004/7OK12.2s4.9k / 3.8k
CG-AL-X141hard1100.0 / 10039/39OK12.6s4.4k / 3.9k
CG-AL-X142hard262.5 / 10045/48OK13.5s12k / 9.5k
CG-AL-X143hard1100.0 / 10035/35OK17.9s5.1k / 4.6k
CG-AL-X144hard20.0 / 1000/0FAIL4.8s10k / 8.0k
CG-AL-X145hard1100.0 / 10032/32OK12.4s5.3k / 5.0k
CG-AL-X146hard262.5 / 1006/9OK12.0s4.7k / 3.7k
CG-AL-X147hard1100.0 / 1008/8OK11.9s1.6k / 1.2k
CG-AL-X148hard1100.0 / 1006/6OK11.3s1.4k / 1.0k
CG-AL-X149hard1100.0 / 1007/7OK11.3s1.4k / 1.1k
CG-AL-X150hard262.5 / 1006/9OK12.5s6.9k / 6.1k
CG-AL-X151hard1100.0 / 1006/6OK11.0s999 / 665
CG-AL-X152hard1100.0 / 1008/8OK11.5s1.3k / 879
CG-AL-X153hard262.5 / 1007/9OK14.8s2.9k / 2.4k
CG-AL-X154hard1100.0 / 1009/9OK11.3s1.6k / 1.3k
CG-AL-X155hard1100.0 / 10011/11OK11.3s1.1k / 1.2k
CG-AL-X156hard1100.0 / 1007/7OK11.2s1.1k / 735
CG-AL-X157hard1100.0 / 10010/10OK11.7s1.6k / 1.2k
CG-AL-X158hard1100.0 / 1007/7OK11.4s965 / 573
CG-AL-X159hard1100.0 / 1007/7OK12.6s1.0k / 669
CG-AL-X160hard1100.0 / 10013/13OK12.3s1.5k / 1.5k
CG-AL-X161hard1100.0 / 10010/10OK12.3s1.8k / 1.7k
CG-AL-X162hard1100.0 / 1007/7OK12.0s1.2k / 999
CG-AL-X163hard1100.0 / 1007/7OK11.3s1.3k / 961
CG-AL-X164hard1100.0 / 1007/7OK11.2s1.1k / 807
CG-AL-X165hard262.5 / 10010/13OK13.7s8.1k / 6.5k
CG-AL-X166hard2100.0 / 10014/14OK13.2s4.9k / 2.8k
CG-AL-X167hard262.5 / 1005/13OK11.8s4.4k / 2.7k
CG-AL-X168hard262.5 / 1006/9OK12.3s4.3k / 2.8k
CG-AL-X169hard262.5 / 1007/11OK12.1s4.9k / 3.6k
CG-AL-X170hard262.5 / 1008/11OK12.5s10k / 8.0k
CG-AL-X171hard262.5 / 1008/9OK11.9s4.6k / 4.2k
CG-AL-X172hard2100.0 / 10011/11OK12.1s6.7k / 6.6k
CG-AL-X173hard20.0 / 1000/0FAIL3.8s8.7k / 7.8k
CG-AL-X174hard262.5 / 10013/16OK12.3s11k / 9.7k
CG-AL-X185hard20.0 / 1000/0FAIL4.7s9.9k / 1.5k
CG-AL-X187hard262.5 / 10030/33OK12.6s10k / 2.8k
CG-AL-X194hard262.5 / 10044/50OK12.2s15k / 4.1k
CG-AL-X211hard262.5 / 10036/43OK12.3s13k / 4.7k
CG-AL-X214hard262.5 / 10031/34OK12.3s11k / 2.6k
CG-AL-X218hard262.5 / 10024/27OK12.3s12k / 3.0k
CG-AL-X234hard262.5 / 10032/35OK12.4s12k / 2.1k
CG-AL-X239hard262.5 / 10034/37OK13.0s16k / 2.1k
CG-AL-X244hard2100.0 / 10038/38OK12.8s14k / 4.3k
CG-AL-X245hard262.5 / 10048/63OK13.2s19k / 2.2k
CG-AL-X248hard262.5 / 10042/66OK13.0s19k / 3.4k
CG-AL-X249hard262.5 / 10032/37OK12.7s13k / 2.9k
CG-AL-X254hard262.5 / 10053/70OK13.1s23k / 3.1k
CG-AL-X257hard262.5 / 10045/53OK13.0s15k / 4.7k
CG-AL-X263hard20.0 / 1000/0FAIL4.0s18k / 4.7k
CG-AL-X264hard262.5 / 10060/65OK13.9s17k / 7.6k
CG-AL-X270hard262.5 / 10060/63OK13.5s26k / 4.6k
CG-AL-X271hard20.0 / 1000/0FAIL5.1s19k / 4.7k
CG-AL-X272hard262.5 / 10059/79OK13.6s23k / 4.7k
CG-AL-X274hard262.5 / 10056/64OK13.4s20k / 7.8k
CG-AL-X276hard262.5 / 10057/78OK13.2s23k / 3.9k
CG-AL-X278hard262.5 / 10062/71OK13.4s21k / 3.9k
CG-AL-X283hard20.0 / 1000/0FAIL4.4s25k / 4.1k
CG-AL-X289hard262.5 / 10046/57OK12.9s21k / 5.9k
CG-AL-X290hard20.0 / 1000/0FAIL4.3s13k / 4.1k
CG-AL-X292hard262.5 / 10040/57OK13.5s20k / 2.8k
CG-AL-X293hard20.0 / 1000/0FAIL4.1s16k / 3.7k
CG-AL-X296hard262.5 / 10041/47OK13.6s21k / 6.4k
CG-AL-X298hard20.0 / 1000/0FAIL4.2s19k / 5.9k