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.

47.0% 109/232 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.

45.4 / 100
Cost $3.50
Tokens 948k / 511k input / output, all attempts
Duration 59m 35s
Filter:
Per-task results for run 8e71584d-7ee8-4048-a95c-0224d0428cdf
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK21.7s272 / 231
CG-AL-E006easy20.0 / 1000/0FAIL10.2s1.4k / 982
CG-AL-E010easy1100.0 / 1005/5OK22.8s299 / 124
CG-AL-E050easy20.0 / 1000/0FAIL9.7s2.2k / 451
CG-AL-E052easy1100.0 / 10016/16OK14.1s391 / 282
CG-AL-E054easy20.0 / 1000/0FAIL10.1s1.2k / 490
CG-AL-E056easy262.5 / 10013/15OK18.4s1.9k / 694
CG-AL-H007hard2100.0 / 10011/11OK17.9s2.0k / 1.3k
CG-AL-H011hard20.0 / 1000/0FAIL4.3s1.4k / 423
CG-AL-H014hard20.0 / 1000/0FAIL4.3s1.6k / 884
CG-AL-H017hard20.0 / 1000/0FAIL4.2s1.2k / 560
CG-AL-H020hard2100.0 / 10010/10OK12.4s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL4.3s3.0k / 1.6k
CG-AL-H023hard20.0 / 1000/0FAIL5.6s7.9k / 8.6k
CG-AL-H027hard262.5 / 1002/4OK12.0s2.6k / 819
CG-AL-H029hard20.0 / 1000/0FAIL4.4s3.4k / 2.3k
CG-AL-H030hard20.0 / 1000/0FAIL4.5s2.4k / 1.3k
CG-AL-H031hard2100.0 / 10022/22OK11.8s3.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK11.8s1.5k / 338
CG-AL-H036hard20.0 / 1000/0FAIL4.4s1.3k / 332
CG-AL-H037hard20.0 / 1000/0FAIL4.4s1.6k / 402
CG-AL-H041hard20.0 / 1000/0FAIL4.5s2.1k / 1.2k
CG-AL-H050hard262.5 / 1002/3OK12.0s1.4k / 433
CG-AL-H054hard2100.0 / 1005/5OK11.5s2.7k / 1.9k
CG-AL-H056hard20.0 / 1000/0FAIL4.3s1.7k / 330
CG-AL-M001medium20.0 / 1000/0FAIL4.1s1.9k / 1.0k
CG-AL-M003medium20.0 / 1000/0FAIL4.3s1.8k / 1.7k
CG-AL-M004medium1100.0 / 10012/12OK40.0s496 / 1.2k
CG-AL-M006medium262.5 / 10017/18OK12.8s2.4k / 2.4k
CG-AL-M007medium20.0 / 1000/0FAIL4.2s3.7k / 4.3k
CG-AL-M008medium20.0 / 1000/0FAIL4.3s5.1k / 6.4k
CG-AL-M009medium1100.0 / 10011/11OK14.3s475 / 3.5k
CG-AL-M010medium262.5 / 10020/21OK25.6s3.5k / 4.0k
CG-AL-M020medium2100.0 / 10017/17OK11.5s3.2k / 1.9k
CG-AL-M023medium1100.0 / 10011/11OK16.2s536 / 547
CG-AL-M025medium262.5 / 1002/8OK12.4s1.4k / 780
CG-AL-M026medium1100.0 / 1008/8OK14.4s426 / 347
CG-AL-M027medium20.0 / 1000/0FAIL4.1s4.6k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK26.5s1.2k / 610
CG-AL-M031medium20.0 / 1000/0FAIL4.1s2.6k / 1.4k
CG-AL-M034medium266.7 / 1000/2OK12.1s1.5k / 392
CG-AL-M036medium211.1 / 1000/0FAIL4.3s1.7k / 654
CG-AL-M040medium2100.0 / 1002/2OK11.3s917 / 359
CG-AL-M042medium2100.0 / 1008/8OK11.5s3.0k / 759
CG-AL-X001hard262.5 / 1001/2OK11.9s1.1k / 176
CG-AL-X002hard20.0 / 1000/0FAIL4.6s1.6k / 936
CG-AL-X003hard262.5 / 1002/3OK11.6s718 / 309
CG-AL-X004medium1100.0 / 1003/3OK14.7s387 / 245
CG-AL-X005hard1100.0 / 1002/2OK13.9s352 / 188
CG-AL-X006hard2100.0 / 1003/3OK11.5s1.5k / 682
CG-AL-X007hard1100.0 / 1002/2OK2m 2s400 / 262
CG-AL-X008hard20.0 / 1000/0FAIL4.7s1.9k / 1.0k
CG-AL-X009medium1100.0 / 1002/2OK15.0s334 / 128
CG-AL-X010medium1100.0 / 1003/3OK15.8s306 / 147
CG-AL-X011medium1100.0 / 1002/2OK14.3s396 / 162
CG-AL-X012hard20.0 / 1000/0FAIL4.6s1.7k / 609
CG-AL-X013hard1100.0 / 1002/2OK14.9s286 / 90
CG-AL-X014medium1100.0 / 1004/4OK14.6s313 / 91
CG-AL-X017medium20.0 / 1000/0FAIL0ms1.7k / 64k
CG-AL-X018medium1100.0 / 1003/3OK14.5s420 / 173
CG-AL-X019medium262.5 / 1000/3OK12.1s2.1k / 661
CG-AL-X022medium2100.0 / 1003/3OK11.4s1.5k / 474
CG-AL-X024medium1100.0 / 1003/3OK13.8s371 / 352
CG-AL-X025medium1100.0 / 1001/1OK13.9s413 / 330
CG-AL-X026medium1100.0 / 1003/3OK14.5s353 / 184
CG-AL-X027medium2100.0 / 1004/4OK11.9s825 / 380
CG-AL-X029medium1100.0 / 1002/2OK15.0s304 / 171
CG-AL-X030medium1100.0 / 1002/2OK13.8s271 / 102
CG-AL-X031medium1100.0 / 1003/3OK14.8s321 / 174
CG-AL-X033hard1100.0 / 1002/2OK15.0s380 / 134
CG-AL-X034hard1100.0 / 1003/3OK15.3s333 / 144
CG-AL-X035hard262.5 / 1000/3OK11.6s1.0k / 418
CG-AL-X037hard20.0 / 1000/0FAIL4.6s1.2k / 527
CG-AL-X040hard20.0 / 1000/0FAIL4.3s1.7k / 858
CG-AL-X041hard20.0 / 1000/0FAIL4.4s1.4k / 751
CG-AL-X043hard20.0 / 1000/0FAIL4.3s1.6k / 1.3k
CG-AL-X044hard262.5 / 1000/3OK11.9s1.4k / 763
CG-AL-X045hard262.5 / 1000/3OK11.8s2.0k / 774
CG-AL-X046hard262.5 / 1000/2OK11.6s1.7k / 586
CG-AL-X047hard10.0 / 1000/0FAIL5.6s441 / 889
CG-AL-X050hard20.0 / 1000/0FAIL610ms1.9k / 842
CG-AL-X051hard20.0 / 1000/0FAIL598ms2.1k / 913
CG-AL-X052hard162.5 / 1000/3OK14.9s394 / 140
CG-AL-X055hard1100.0 / 1005/5OK14.9s370 / 333
CG-AL-X056hard1100.0 / 1005/5OK14.5s297 / 157
CG-AL-X057hard1100.0 / 1005/5OK14.0s274 / 125
CG-AL-X058hard1100.0 / 1005/5OK15.1s347 / 262
CG-AL-X059hard1100.0 / 1003/3OK14.3s361 / 83
CG-AL-X060hard162.5 / 1000/3OK14.2s331 / 139
CG-AL-X061hard162.5 / 1002/4OK15.3s396 / 113
CG-AL-X062hard1100.0 / 1004/4OK15.0s411 / 370
CG-AL-X063hard10.0 / 1000/0FAIL6.2s392 / 227
CG-AL-X064hard1100.0 / 1007/7OK13.8s300 / 288
CG-AL-X065hard1100.0 / 1006/6OK15.0s868 / 650
CG-AL-X066hard1100.0 / 10014/14OK13.9s1.7k / 1.4k
CG-AL-X067hard20.0 / 1000/0FAIL129ms1.9k / 917
CG-AL-X068hard20.0 / 1000/0FAIL139ms2.9k / 2.1k
CG-AL-X069hard20.0 / 1000/0FAIL142ms3.1k / 2.3k
CG-AL-X070hard1100.0 / 10012/12OK15.4s1.4k / 877
CG-AL-X071hard1100.0 / 1008/8OK14.5s1.7k / 1.4k
CG-AL-X072hard1100.0 / 1007/7OK14.2s1.4k / 1.1k
CG-AL-X073hard1100.0 / 1008/8OK14.2s1.8k / 1.6k
CG-AL-X074hard1100.0 / 1007/7OK14.5s1.9k / 1.6k
CG-AL-X075hard20.0 / 1000/0FAIL255ms4.2k / 1.6k
CG-AL-X076hard20.0 / 1000/0FAIL254ms4.2k / 1.6k
CG-AL-X077hard20.0 / 1000/0FAIL378ms4.3k / 3.5k
CG-AL-X078hard1100.0 / 10017/17OK14.2s1.5k / 1.2k
CG-AL-X079hard20.0 / 1000/0FAIL257ms4.0k / 3.0k
CG-AL-X080hard20.0 / 1000/0FAIL258ms3.1k / 2.4k
CG-AL-X081hard1100.0 / 1008/8OK14.9s1.1k / 741
CG-AL-X082hard20.0 / 1000/0FAIL129ms3.2k / 2.3k
CG-AL-X083hard1100.0 / 1009/9OK15.3s2.0k / 1.6k
CG-AL-X084hard20.0 / 1000/0FAIL302ms4.1k / 3.0k
CG-AL-X085hard20.0 / 1000/0FAIL304ms3.4k / 1.4k
CG-AL-X086hard20.0 / 1000/0FAIL132ms4.1k / 3.7k
CG-AL-X087hard1100.0 / 1003/3OK14.5s1.3k / 1.0k
CG-AL-X088hard1100.0 / 1006/6OK15.1s1.2k / 956
CG-AL-X089hard20.0 / 1000/0FAIL259ms3.2k / 2.5k
CG-AL-X090hard20.0 / 1000/0FAIL257ms3.3k / 2.9k
CG-AL-X091hard1100.0 / 1006/6OK14.4s699 / 879
CG-AL-X092hard20.0 / 1000/0FAIL131ms2.5k / 925
CG-AL-X093hard20.0 / 1000/0FAIL254ms2.8k / 2.1k
CG-AL-X094hard1100.0 / 1007/7OK14.0s944 / 654
CG-AL-X095hard1100.0 / 1005/5OK14.8s957 / 693
CG-AL-X096hard20.0 / 1000/0FAIL130ms9.0k / 8.1k
CG-AL-X097hard20.0 / 1000/0FAIL249ms9.6k / 9.0k
CG-AL-X098hard1100.0 / 10029/29OK16.5s3.4k / 2.9k
CG-AL-X099hard20.0 / 1000/0FAIL244ms10k / 8.4k
CG-AL-X100hard1100.0 / 10035/35OK16.0s4.4k / 3.9k
CG-AL-X101hard1100.0 / 10010/10OK14.4s1.3k / 1.0k
CG-AL-X102hard1100.0 / 1008/8OK14.8s615 / 339
CG-AL-X103hard1100.0 / 1007/7OK14.3s891 / 596
CG-AL-X104hard1100.0 / 1006/6OK15.1s1.3k / 1.0k
CG-AL-X105hard1100.0 / 1006/6OK14.6s963 / 601
CG-AL-X106hard1100.0 / 1005/5OK13.8s1.1k / 836
CG-AL-X107hard1100.0 / 1004/4OK13.8s1.0k / 801
CG-AL-X108hard1100.0 / 1006/6OK15.3s865 / 457
CG-AL-X109hard1100.0 / 1005/5OK15.1s638 / 321
CG-AL-X110hard1100.0 / 10017/17OK14.7s1.5k / 1.3k
CG-AL-X111hard1100.0 / 1008/8OK14.0s1.4k / 1.1k
CG-AL-X112hard20.0 / 1000/0FAIL138ms2.7k / 3.4k
CG-AL-X113hard1100.0 / 10013/13OK15.3s897 / 566
CG-AL-X114hard1100.0 / 1007/7OK14.2s909 / 557
CG-AL-X115hard20.0 / 1000/0FAIL254ms1.7k / 704
CG-AL-X116hard20.0 / 1000/0FAIL246ms5.1k / 1.5k
CG-AL-X117hard1100.0 / 1008/8OK14.4s1.2k / 957
CG-AL-X118hard1100.0 / 10017/17OK15.1s1.8k / 1.4k
CG-AL-X119hard1100.0 / 10015/15OK15.2s2.1k / 2.0k
CG-AL-X120hard1100.0 / 10012/12OK14.3s1.6k / 1.4k
CG-AL-X121hard1100.0 / 1006/6OK14.5s1.2k / 989
CG-AL-X122hard20.0 / 1000/0FAIL307ms4.2k / 3.7k
CG-AL-X123hard20.0 / 1000/0FAIL309ms1.6k / 680
CG-AL-X124hard1100.0 / 10010/10OK14.5s1.2k / 875
CG-AL-X125hard1100.0 / 1008/8OK14.7s1.7k / 1.4k
CG-AL-X126hard20.0 / 1000/0FAIL132ms1.9k / 835
CG-AL-X127hard1100.0 / 1005/5OK14.8s807 / 489
CG-AL-X128hard1100.0 / 1008/8OK14.0s1.4k / 1.0k
CG-AL-X129hard1100.0 / 10014/14OK14.6s1.5k / 1.3k
CG-AL-X130hard20.0 / 1000/0FAIL247ms1.4k / 609
CG-AL-X131hard1100.0 / 10013/13OK14.0s1.1k / 685
CG-AL-X132hard1100.0 / 10010/10OK13.7s865 / 548
CG-AL-X133hard20.0 / 1000/0FAIL249ms4.2k / 3.7k
CG-AL-X134hard1100.0 / 1006/6OK15.5s1.5k / 1.2k
CG-AL-X135hard1100.0 / 1004/4OK13.7s1.0k / 706
CG-AL-X136hard1100.0 / 1007/7OK14.2s889 / 390
CG-AL-X137hard1100.0 / 1004/4OK14.9s1.1k / 724
CG-AL-X138hard1100.0 / 1009/9OK14.5s1.7k / 1.5k
CG-AL-X139hard1100.0 / 10011/11OK14.7s2.0k / 1.9k
CG-AL-X140hard20.0 / 1000/0FAIL134ms4.9k / 3.7k
CG-AL-X141hard1100.0 / 10039/39OK15.3s4.4k / 3.9k
CG-AL-X142hard20.0 / 1000/0FAIL256ms12k / 5.7k
CG-AL-X143hard1100.0 / 10035/35OK20.9s5.1k / 4.6k
CG-AL-X144hard20.0 / 1000/0FAIL254ms10k / 8.0k
CG-AL-X145hard1100.0 / 10032/32OK15.4s5.3k / 5.0k
CG-AL-X146hard20.0 / 1000/0FAIL130ms4.9k / 4.1k
CG-AL-X147hard1100.0 / 1008/8OK15.2s1.6k / 1.2k
CG-AL-X148hard1100.0 / 1006/6OK14.1s1.4k / 1.0k
CG-AL-X149hard1100.0 / 1007/7OK14.2s1.4k / 1.1k
CG-AL-X150hard20.0 / 1000/0FAIL283ms7.5k / 6.3k
CG-AL-X151hard1100.0 / 1006/6OK15.2s999 / 665
CG-AL-X152hard1100.0 / 1008/8OK14.9s1.3k / 879
CG-AL-X153hard20.0 / 1000/0FAIL281ms2.9k / 2.0k
CG-AL-X154hard1100.0 / 1009/9OK14.7s1.6k / 1.3k
CG-AL-X155hard1100.0 / 10011/11OK14.0s1.1k / 1.2k
CG-AL-X156hard1100.0 / 1007/7OK15.0s1.1k / 735
CG-AL-X157hard20.0 / 1000/0FAIL145ms3.3k / 2.4k
CG-AL-X158hard1100.0 / 1007/7OK14.1s965 / 573
CG-AL-X159hard1100.0 / 1007/7OK14.6s1.0k / 669
CG-AL-X160hard1100.0 / 10013/13OK14.6s1.5k / 1.5k
CG-AL-X161hard1100.0 / 10010/10OK14.7s1.8k / 1.7k
CG-AL-X162hard1100.0 / 1007/7OK14.8s1.2k / 994
CG-AL-X163hard1100.0 / 1007/7OK14.9s1.3k / 961
CG-AL-X164hard1100.0 / 1007/7OK14.5s1.1k / 807
CG-AL-X165hard20.0 / 1000/0FAIL305ms8.1k / 6.5k
CG-AL-X166hard20.0 / 1000/0FAIL303ms4.9k / 2.8k
CG-AL-X167hard20.0 / 1000/0FAIL269ms4.4k / 2.8k
CG-AL-X168hard20.0 / 1000/0FAIL392ms4.4k / 2.9k
CG-AL-X169hard20.0 / 1000/0FAIL394ms4.9k / 3.5k
CG-AL-X170hard20.0 / 1000/0FAIL385ms9.7k / 6.8k
CG-AL-X171hard20.0 / 1000/0FAIL265ms4.2k / 3.7k
CG-AL-X172hard20.0 / 1000/0FAIL391ms6.8k / 6.7k
CG-AL-X173hard20.0 / 1000/0FAIL259ms8.8k / 8.1k
CG-AL-X174hard20.0 / 1000/0FAIL253ms11k / 9.4k
CG-AL-X185hard20.0 / 1000/0FAIL134ms9.1k / 2.4k
CG-AL-X187hard20.0 / 1000/0FAIL255ms10k / 3.1k
CG-AL-X194hard20.0 / 1000/0FAIL251ms15k / 4.2k
CG-AL-X211hard20.0 / 1000/0FAIL192ms13k / 5.2k
CG-AL-X214hard20.0 / 1000/0FAIL262ms11k / 2.7k
CG-AL-X218hard20.0 / 1000/0FAIL255ms12k / 3.0k
CG-AL-X234hard20.0 / 1000/0FAIL259ms12k / 2.1k
CG-AL-X239hard20.0 / 1000/0FAIL125ms16k / 3.2k
CG-AL-X244hard20.0 / 1000/0FAIL258ms15k / 4.0k
CG-AL-X245hard20.0 / 1000/0FAIL267ms19k / 2.2k
CG-AL-X248hard20.0 / 1000/0FAIL129ms19k / 2.8k
CG-AL-X249hard20.0 / 1000/0FAIL259ms13k / 3.4k
CG-AL-X254hard20.0 / 1000/0FAIL265ms23k / 2.9k
CG-AL-X257hard20.0 / 1000/0FAIL260ms15k / 4.7k
CG-AL-X263hard20.0 / 1000/0FAIL135ms12k / 3.4k
CG-AL-X264hard20.0 / 1000/0FAIL267ms17k / 7.1k
CG-AL-X270hard20.0 / 1000/0FAIL269ms26k / 4.1k
CG-AL-X271hard20.0 / 1000/0FAIL129ms19k / 4.6k
CG-AL-X272hard20.0 / 1000/0FAIL281ms23k / 4.7k
CG-AL-X274hard20.0 / 1000/0FAIL279ms20k / 7.9k
CG-AL-X276hard20.0 / 1000/0FAIL256ms23k / 3.8k
CG-AL-X278hard20.0 / 1000/0FAIL132ms21k / 4.0k
CG-AL-X283hard20.0 / 1000/0FAIL136ms25k / 4.6k
CG-AL-X289hard20.0 / 1000/0FAIL128ms19k / 5.7k
CG-AL-X290hard20.0 / 1000/0FAIL129ms13k / 4.2k
CG-AL-X292hard20.0 / 1000/0FAIL140ms20k / 2.8k
CG-AL-X293hard20.0 / 1000/0FAIL132ms16k / 3.5k
CG-AL-X296hard20.0 / 1000/0FAIL137ms21k / 6.6k
CG-AL-X298hard20.0 / 1000/0FAIL257ms18k / 6.1k