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.

55.8% 129/231 of 231 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.

59.6 / 100
Cost $3.23
Tokens 974k / 451k input / output, all attempts
Duration 1h 20m
Filter:
Per-task results for run 20a0f409-7e1a-4ea8-a060-b3a8429bcf31
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK34.4s272 / 239
CG-AL-E006easy20.0 / 1000/0FAIL13.5s1.1k / 765
CG-AL-E010easy20.0 / 1000/0FAIL13.6s783 / 230
CG-AL-E050easy20.0 / 1000/0FAIL12.9s2.2k / 451
CG-AL-E052easy1100.0 / 10016/16OK15.8s391 / 282
CG-AL-E054easy20.0 / 1000/0FAIL12.1s1.2k / 490
CG-AL-E056easy262.5 / 10013/15OK17.1s1.9k / 694
CG-AL-H007hard2100.0 / 10011/11OK16.4s2.0k / 1.3k
CG-AL-H011hard20.0 / 1000/0FAIL5.3s1.4k / 428
CG-AL-H014hard20.0 / 1000/0FAIL5.4s1.6k / 884
CG-AL-H017hard20.0 / 1000/0FAIL5.0s1.2k / 530
CG-AL-H020hard20.0 / 1000/0FAIL5.8s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL6.3s3.0k / 1.6k
CG-AL-H023hard20.0 / 1000/0FAIL5.7s7.3k / 9.1k
CG-AL-H027hard262.5 / 1002/4OK16.0s2.7k / 1.0k
CG-AL-H029hard2100.0 / 10018/18OK15.5s3.4k / 2.4k
CG-AL-H030hard262.5 / 1009/10OK14.3s2.3k / 1.3k
CG-AL-H031hard2100.0 / 10022/22OK16.0s3.3k / 2.3k
CG-AL-H034hard2100.0 / 1003/3OK15.2s1.5k / 338
CG-AL-H036hard2100.0 / 1005/5OK13.9s1.3k / 325
CG-AL-H037hard20.0 / 1000/0FAIL5.6s1.6k / 390
CG-AL-H041hard20.0 / 1000/0FAIL5.8s2.2k / 1.2k
CG-AL-H050hard262.5 / 1002/3OK15.1s1.7k / 421
CG-AL-H054hard2100.0 / 1005/5OK14.9s2.7k / 1.9k
CG-AL-H056hard20.0 / 1000/0FAIL6.1s1.7k / 330
CG-AL-M001medium20.0 / 1000/0FAIL5.0s1.9k / 1.1k
CG-AL-M003medium262.5 / 1000/1OK48.8s1.8k / 1.5k
CG-AL-M004medium1100.0 / 10012/12OK46.5s496 / 1.2k
CG-AL-M006medium1100.0 / 10018/18OK16.7s445 / 972
CG-AL-M007medium20.0 / 1000/0FAIL5.1s3.6k / 4.2k
CG-AL-M008medium20.0 / 1000/0FAIL5.5s6.3k / 7.6k
CG-AL-M009medium2100.0 / 10011/11OK14.2s3.8k / 5.5k
CG-AL-M010medium262.5 / 10020/21OK32.2s3.4k / 3.9k
CG-AL-M020medium20.0 / 1000/0FAIL5.3s2.2k / 1.3k
CG-AL-M023medium1100.0 / 10011/11OK16.8s536 / 541
CG-AL-M025medium262.5 / 1002/8OK14.5s1.4k / 780
CG-AL-M026medium1100.0 / 1008/8OK14.0s426 / 347
CG-AL-M027medium20.0 / 1000/0FAIL6.1s4.5k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK34.2s1.2k / 610
CG-AL-M031medium20.0 / 1000/0FAIL5.4s2.6k / 1.4k
CG-AL-M034medium2100.0 / 1002/2OK15.3s1.5k / 432
CG-AL-M036medium211.1 / 1000/0FAIL5.5s1.7k / 633
CG-AL-M040medium2100.0 / 1002/2OK14.1s917 / 359
CG-AL-M042medium2100.0 / 1008/8OK14.3s3.0k / 729
CG-AL-X001hard262.5 / 1001/2OK14.2s1.1k / 176
CG-AL-X002hard20.0 / 1000/0FAIL6.7s2.2k / 1.0k
CG-AL-X003hard262.5 / 1002/3OK14.1s719 / 309
CG-AL-X004medium1100.0 / 1003/3OK14.4s387 / 245
CG-AL-X005hard1100.0 / 1002/2OK14.6s352 / 190
CG-AL-X006hard2100.0 / 1003/3OK14.5s1.5k / 832
CG-AL-X008hard2100.0 / 1001/1OK15.1s1.9k / 1.0k
CG-AL-X009medium1100.0 / 1002/2OK14.2s334 / 128
CG-AL-X010medium1100.0 / 1003/3OK15.1s306 / 159
CG-AL-X011medium1100.0 / 1002/2OK14.4s396 / 162
CG-AL-X012hard20.0 / 1000/0FAIL5.8s1.8k / 683
CG-AL-X013hard1100.0 / 1002/2OK13.6s286 / 90
CG-AL-X014medium1100.0 / 1004/4OK14.4s313 / 91
CG-AL-X017medium2100.0 / 1003/3OK13.7s1.7k / 1.6k
CG-AL-X018medium1100.0 / 1003/3OK14.3s420 / 173
CG-AL-X019medium2100.0 / 1003/3OK14.3s2.1k / 742
CG-AL-X022medium2100.0 / 1003/3OK13.8s1.5k / 474
CG-AL-X024medium1100.0 / 1003/3OK14.4s371 / 348
CG-AL-X025medium1100.0 / 1001/1OK16.0s413 / 342
CG-AL-X026medium1100.0 / 1003/3OK13.8s353 / 184
CG-AL-X027medium2100.0 / 1004/4OK14.8s824 / 380
CG-AL-X029medium1100.0 / 1002/2OK15.6s304 / 173
CG-AL-X030medium1100.0 / 1002/2OK14.8s271 / 102
CG-AL-X031medium1100.0 / 1003/3OK14.3s321 / 174
CG-AL-X033hard1100.0 / 1002/2OK14.8s380 / 134
CG-AL-X034hard1100.0 / 1003/3OK14.7s333 / 144
CG-AL-X035hard262.5 / 1000/3OK14.9s1.0k / 403
CG-AL-X037hard20.0 / 1000/0FAIL5.7s1.2k / 517
CG-AL-X040hard20.0 / 1000/0FAIL5.6s1.7k / 867
CG-AL-X041hard20.0 / 1000/0FAIL5.4s1.4k / 738
CG-AL-X043hard20.0 / 1000/0FAIL5.4s1.6k / 1.3k
CG-AL-X044hard262.5 / 1000/3OK14.2s1.2k / 671
CG-AL-X045hard262.5 / 1000/3OK14.8s2.0k / 755
CG-AL-X046hard262.5 / 1000/2OK14.5s1.9k / 572
CG-AL-X047hard262.5 / 1001/2OK14.5s1.9k / 1.8k
CG-AL-X050hard262.5 / 1000/2OK14.3s1.9k / 1.0k
CG-AL-X051hard262.5 / 1000/2OK14.0s2.1k / 893
CG-AL-X052hard262.5 / 1000/3OK14.4s2.0k / 479
CG-AL-X055hard1100.0 / 1005/5OK14.7s370 / 318
CG-AL-X056hard1100.0 / 1005/5OK14.4s297 / 157
CG-AL-X057hard1100.0 / 1005/5OK14.1s274 / 114
CG-AL-X058hard1100.0 / 1005/5OK14.8s347 / 262
CG-AL-X059hard1100.0 / 1003/3OK14.1s361 / 83
CG-AL-X060hard2100.0 / 1003/3OK14.3s1.8k / 246
CG-AL-X061hard2100.0 / 1004/4OK14.4s1.5k / 331
CG-AL-X062hard1100.0 / 1004/4OK14.7s411 / 412
CG-AL-X063hard20.0 / 1000/0FAIL5.7s1.0k / 378
CG-AL-X064hard1100.0 / 1007/7OK14.0s300 / 288
CG-AL-X065hard1100.0 / 1006/6OK14.4s868 / 650
CG-AL-X066hard1100.0 / 10014/14OK14.8s1.7k / 1.4k
CG-AL-X067hard262.5 / 1006/7OK13.6s1.9k / 917
CG-AL-X068hard262.5 / 1003/12OK14.9s2.9k / 2.1k
CG-AL-X069hard262.5 / 1006/8OK14.2s3.0k / 2.0k
CG-AL-X070hard1100.0 / 10012/12OK14.2s1.4k / 877
CG-AL-X071hard1100.0 / 1008/8OK15.4s1.7k / 1.4k
CG-AL-X072hard1100.0 / 1007/7OK14.4s1.4k / 1.1k
CG-AL-X073hard1100.0 / 1008/8OK14.4s1.8k / 1.6k
CG-AL-X074hard1100.0 / 1007/7OK14.7s1.9k / 1.6k
CG-AL-X075hard20.0 / 1000/0FAIL5.5s4.2k / 1.7k
CG-AL-X076hard2100.0 / 10014/14OK15.3s4.2k / 1.6k
CG-AL-X077hard2100.0 / 10022/22OK15.2s4.3k / 3.9k
CG-AL-X078hard1100.0 / 10017/17OK14.5s1.5k / 1.2k
CG-AL-X079hard262.5 / 1008/11OK14.0s4.0k / 3.0k
CG-AL-X080hard20.0 / 1000/0FAIL5.4s3.1k / 2.3k
CG-AL-X081hard1100.0 / 1008/8OK15.0s1.1k / 741
CG-AL-X082hard2100.0 / 10015/15OK14.6s3.2k / 2.3k
CG-AL-X083hard1100.0 / 1009/9OK14.0s2.0k / 1.6k
CG-AL-X084hard2100.0 / 10010/10OK15.5s4.1k / 3.0k
CG-AL-X085hard1100.0 / 1007/7OK15.1s1.2k / 789
CG-AL-X086hard2100.0 / 1006/6OK14.2s5.4k / 4.1k
CG-AL-X087hard1100.0 / 1003/3OK14.9s1.3k / 972
CG-AL-X088hard1100.0 / 1006/6OK14.0s1.2k / 956
CG-AL-X089hard2100.0 / 10011/11OK14.5s3.2k / 2.5k
CG-AL-X090hard262.5 / 1008/10OK14.8s3.3k / 2.8k
CG-AL-X091hard1100.0 / 1006/6OK14.2s699 / 879
CG-AL-X092hard2100.0 / 10015/15OK14.0s2.4k / 869
CG-AL-X093hard262.5 / 1009/10OK14.2s2.8k / 2.2k
CG-AL-X094hard1100.0 / 1007/7OK14.1s944 / 680
CG-AL-X095hard1100.0 / 1005/5OK15.1s957 / 693
CG-AL-X096hard262.5 / 10044/49OK14.7s9.0k / 8.2k
CG-AL-X097hard1100.0 / 10046/46OK14.9s4.5k / 4.2k
CG-AL-X098hard1100.0 / 10029/29OK15.1s3.4k / 3.0k
CG-AL-X099hard2100.0 / 10039/39OK17.2s10.0k / 9.0k
CG-AL-X100hard1100.0 / 10035/35OK17.0s4.4k / 3.9k
CG-AL-X101hard1100.0 / 10010/10OK14.0s1.3k / 1.0k
CG-AL-X102hard1100.0 / 1008/8OK13.8s615 / 339
CG-AL-X103hard1100.0 / 1007/7OK13.9s891 / 596
CG-AL-X104hard1100.0 / 1006/6OK14.4s1.3k / 1.0k
CG-AL-X105hard1100.0 / 1006/6OK14.7s963 / 598
CG-AL-X106hard1100.0 / 1005/5OK14.2s1.1k / 836
CG-AL-X107hard1100.0 / 1004/4OK14.1s1.0k / 801
CG-AL-X108hard1100.0 / 1006/6OK14.6s865 / 457
CG-AL-X109hard1100.0 / 1005/5OK14.3s638 / 321
CG-AL-X110hard1100.0 / 10017/17OK14.6s1.5k / 1.3k
CG-AL-X111hard1100.0 / 1008/8OK14.1s1.4k / 1.1k
CG-AL-X112hard262.5 / 10011/12OK15.0s2.8k / 2.1k
CG-AL-X113hard1100.0 / 10013/13OK14.5s897 / 567
CG-AL-X114hard1100.0 / 1007/7OK13.9s909 / 557
CG-AL-X115hard20.0 / 1000/0FAIL5.2s1.7k / 681
CG-AL-X116hard2100.0 / 10017/17OK13.7s5.1k / 1.5k
CG-AL-X117hard1100.0 / 1008/8OK15.2s1.2k / 957
CG-AL-X118hard262.5 / 1009/17OK15.3s7.5k / 3.1k
CG-AL-X119hard1100.0 / 10015/15OK15.1s2.1k / 2.0k
CG-AL-X120hard1100.0 / 10012/12OK14.1s1.6k / 1.4k
CG-AL-X121hard1100.0 / 1006/6OK14.0s1.2k / 989
CG-AL-X122hard262.5 / 1009/10OK14.5s4.2k / 3.8k
CG-AL-X123hard20.0 / 1000/0FAIL6.0s1.6k / 680
CG-AL-X124hard1100.0 / 10010/10OK14.1s1.2k / 875
CG-AL-X125hard1100.0 / 1008/8OK15.5s1.7k / 1.4k
CG-AL-X126hard2100.0 / 10014/14OK15.1s4.1k / 1.0k
CG-AL-X127hard1100.0 / 1005/5OK14.0s807 / 489
CG-AL-X128hard1100.0 / 1008/8OK14.4s1.4k / 1.0k
CG-AL-X129hard1100.0 / 10014/14OK14.2s1.5k / 1.3k
CG-AL-X130hard20.0 / 1000/0FAIL5.2s1.4k / 609
CG-AL-X131hard2100.0 / 10013/13OK14.0s5.5k / 1.4k
CG-AL-X132hard1100.0 / 10010/10OK14.4s865 / 548
CG-AL-X133hard262.5 / 1007/8OK14.7s4.2k / 3.3k
CG-AL-X134hard1100.0 / 1006/6OK15.3s1.5k / 1.2k
CG-AL-X135hard1100.0 / 1004/4OK14.7s1.0k / 706
CG-AL-X136hard1100.0 / 1007/7OK15.4s889 / 390
CG-AL-X137hard1100.0 / 1004/4OK13.9s1.1k / 724
CG-AL-X138hard1100.0 / 1009/9OK14.7s1.7k / 1.5k
CG-AL-X139hard1100.0 / 10011/11OK14.3s2.0k / 1.9k
CG-AL-X140hard20.0 / 1000/0FAIL5.6s5.0k / 3.7k
CG-AL-X141hard1100.0 / 10039/39OK15.3s4.4k / 3.9k
CG-AL-X142hard262.5 / 10045/48OK15.4s12k / 9.6k
CG-AL-X143hard1100.0 / 10035/35OK20.6s5.1k / 4.5k
CG-AL-X144hard20.0 / 1000/0FAIL6.2s10k / 8.1k
CG-AL-X145hard1100.0 / 10032/32OK16.3s5.3k / 5.0k
CG-AL-X146hard262.5 / 1006/9OK15.0s4.8k / 4.4k
CG-AL-X147hard1100.0 / 1008/8OK14.6s1.6k / 1.2k
CG-AL-X148hard1100.0 / 1006/6OK14.0s1.4k / 1.0k
CG-AL-X149hard1100.0 / 1007/7OK14.9s1.4k / 1.1k
CG-AL-X150hard262.5 / 1006/9OK14.4s7.2k / 6.3k
CG-AL-X151hard1100.0 / 1006/6OK14.8s999 / 665
CG-AL-X152hard1100.0 / 1008/8OK14.4s1.3k / 879
CG-AL-X153hard262.5 / 1007/9OK17.5s2.9k / 1.9k
CG-AL-X154hard1100.0 / 1009/9OK15.3s1.6k / 1.3k
CG-AL-X155hard1100.0 / 10011/11OK14.5s1.1k / 1.0k
CG-AL-X156hard1100.0 / 1007/7OK32.8s1.1k / 735
CG-AL-X157hard1100.0 / 10010/10OK13.8s1.6k / 1.2k
CG-AL-X158hard1100.0 / 1007/7OK14.0s965 / 573
CG-AL-X159hard1100.0 / 1007/7OK14.8s1.0k / 669
CG-AL-X160hard1100.0 / 10013/13OK14.2s1.5k / 1.5k
CG-AL-X161hard1100.0 / 10010/10OK14.7s1.8k / 1.7k
CG-AL-X162hard1100.0 / 1007/7OK32.6s1.2k / 999
CG-AL-X163hard1100.0 / 1007/7OK14.5s1.3k / 961
CG-AL-X164hard1100.0 / 1007/7OK14.3s1.1k / 807
CG-AL-X165hard262.5 / 10010/13OK16.4s8.1k / 5.9k
CG-AL-X166hard2100.0 / 10014/14OK16.3s4.9k / 2.8k
CG-AL-X167hard262.5 / 1000/13OK15.0s4.4k / 2.6k
CG-AL-X168hard162.5 / 1005/9OK15.0s1.6k / 1.6k
CG-AL-X169hard262.5 / 1009/11OK15.2s4.9k / 3.5k
CG-AL-X170hard262.5 / 1008/11OK14.7s9.7k / 6.7k
CG-AL-X171hard262.5 / 1008/9OK15.2s4.8k / 4.7k
CG-AL-X172hard2100.0 / 10011/11OK14.8s6.6k / 6.4k
CG-AL-X173hard20.0 / 1000/0FAIL5.8s8.8k / 8.9k
CG-AL-X174hard262.5 / 10013/16OK14.9s11k / 9.4k
CG-AL-X185hard20.0 / 1000/0FAIL6.3s9.9k / 1.6k
CG-AL-X187hard262.5 / 10030/33OK15.3s10k / 2.8k
CG-AL-X194hard262.5 / 10044/50OK15.3s15k / 3.7k
CG-AL-X211hard2100.0 / 10043/43OK17.3s13k / 4.8k
CG-AL-X214hard262.5 / 10031/34OK15.5s11k / 2.7k
CG-AL-X218hard262.5 / 10024/27OK15.6s12k / 2.5k
CG-AL-X234hard262.5 / 10032/35OK15.1s12k / 2.0k
CG-AL-X239hard262.5 / 10034/37OK16.5s16k / 2.1k
CG-AL-X244hard262.5 / 10035/38OK15.9s15k / 4.0k
CG-AL-X245hard262.5 / 10046/63OK16.5s19k / 2.3k
CG-AL-X248hard262.5 / 10056/66OK16.6s19k / 3.4k
CG-AL-X249hard262.5 / 10034/37OK15.8s13k / 2.8k
CG-AL-X254hard262.5 / 10052/70OK16.1s23k / 3.3k
CG-AL-X257hard262.5 / 10045/53OK15.9s15k / 4.7k
CG-AL-X263hard262.5 / 10058/61OK16.4s18k / 5.2k
CG-AL-X264hard20.0 / 1000/0FAIL5.7s17k / 4.3k
CG-AL-X270hard262.5 / 10060/63OK17.0s24k / 5.6k
CG-AL-X271hard262.5 / 10053/70OK17.5s26k / 8.3k
CG-AL-X272hard20.0 / 1000/0FAIL5.5s23k / 4.7k
CG-AL-X274hard262.5 / 10056/64OK16.4s20k / 7.8k
CG-AL-X276hard262.5 / 10068/78OK17.6s23k / 3.7k
CG-AL-X278hard262.5 / 10062/71OK17.5s21k / 4.0k
CG-AL-X283hard20.0 / 1000/0FAIL6.5s25k / 4.6k
CG-AL-X289hard262.5 / 10046/57OK12.5s21k / 6.0k
CG-AL-X290hard20.0 / 1000/0FAIL4.8s13k / 4.1k
CG-AL-X292hard262.5 / 10036/57OK15.4s20k / 2.8k
CG-AL-X293hard20.0 / 1000/0FAIL5.3s16k / 3.3k
CG-AL-X296hard262.5 / 10041/47OK17.3s21k / 5.8k
CG-AL-X298hard20.0 / 1000/0FAIL5.8s19k / 5.9k