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.

80.5% 186/231 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.

71.8 / 100
Cost $19.86
Tokens 1.1M / 1.8M input / output, all attempts
Duration 57m 49s
Filter:
Per-task results for run a1d5ecf0-e656-4fbb-985a-2b3a1e3616e1
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.8s413 / 322
CG-AL-E006easy1100.0 / 1007/7OK30.2s494 / 829
CG-AL-E010easy2100.0 / 1005/5OK18.4s1.2k / 510
CG-AL-E050easy20.0 / 1000/0FAIL9.3s3.0k / 1.3k
CG-AL-E052easy1100.0 / 10016/16OK11.1s610 / 378
CG-AL-E054easy2100.0 / 1009/9OK18.4s1.7k / 870
CG-AL-E056easy262.5 / 10013/15OK16.7s2.8k / 1.4k
CG-AL-H007hard1100.0 / 10011/11OK10.7s947 / 2.2k
CG-AL-H011hard1100.0 / 1006/6OK11.2s574 / 234
CG-AL-H014hard2100.0 / 1007/7OK12.8s4.1k / 4.9k
CG-AL-H017hard20.0 / 1000/0FAIL10.1s1.7k / 1.7k
CG-AL-H020hard2100.0 / 10010/10OK10.7s3.5k / 2.5k
CG-AL-H021hard2100.0 / 10020/20OK10.8s30k / 3.7k
CG-AL-H023hard20.0 / 1000/0FAIL4.1s11k / 47k
CG-AL-H027hard262.5 / 1002/4OK11.9s3.4k / 7.5k
CG-AL-H029hard262.5 / 10015/18OK11.0s4.6k / 10k
CG-AL-H030hard1100.0 / 10010/10OK11.2s1.1k / 3.3k
CG-AL-H031hard2100.0 / 10022/22OK11.2s5.3k / 4.9k
CG-AL-H034hard2100.0 / 1003/3OK10.9s2.1k / 754
CG-AL-H036hard20.0 / 1000/0FAIL4.1s1.6k / 615
CG-AL-H041hard262.5 / 1001/3OK10.9s2.6k / 5.9k
CG-AL-H050hard262.5 / 1002/3OK11.1s2.1k / 16k
CG-AL-H054hard20.0 / 1000/0FAIL3.9s3.0k / 1.1k
CG-AL-H056hard2100.0 / 1004/4OK11.0s2.4k / 26k
CG-AL-M001medium2100.0 / 10010/10OK23.5s2.2k / 1.7k
CG-AL-M003medium2100.0 / 1009/9OK17.0s3.4k / 3.5k
CG-AL-M004medium1100.0 / 10012/12OK34.9s773 / 1.5k
CG-AL-M006medium20.0 / 1000/0FAIL4.0s4.3k / 9.5k
CG-AL-M007medium20.0 / 1000/0FAIL4.2s6.1k / 31k
CG-AL-M008medium262.5 / 1006/12OK12.0s9.1k / 39k
CG-AL-M009medium1100.0 / 10011/11OK16.2s746 / 6.6k
CG-AL-M010medium1100.0 / 10021/21OK24.1s958 / 2.8k
CG-AL-M020medium20.0 / 1000/0FAIL3.9s3.1k / 4.2k
CG-AL-M023medium1100.0 / 10011/11OK11.1s803 / 823
CG-AL-M025medium2100.0 / 1008/8OK11.0s4.7k / 9.4k
CG-AL-M026medium2100.0 / 1008/8OK10.9s2.7k / 1.5k
CG-AL-M027medium2100.0 / 10018/18OK11.4s6.3k / 4.5k
CG-AL-M028medium211.1 / 1000/0FAIL3.7s1.5k / 3.5k
CG-AL-M031medium2100.0 / 1002/2OK10.5s3.4k / 2.3k
CG-AL-M034medium1100.0 / 1002/2OK11.3s695 / 1.0k
CG-AL-M036medium211.1 / 1000/0FAIL3.9s2.4k / 1.1k
CG-AL-M040medium20.0 / 1000/0FAIL4.2s1.3k / 914
CG-AL-M042medium1100.0 / 1008/8OK11.0s753 / 548
CG-AL-X001hard1100.0 / 1002/2OK10.7s499 / 216
CG-AL-X002hard262.5 / 1000/4OK11.3s4.1k / 6.5k
CG-AL-X003hard20.0 / 1000/0FAIL3.9s1.5k / 4.9k
CG-AL-X004medium1100.0 / 1003/3OK10.7s551 / 559
CG-AL-X005hard1100.0 / 1002/2OK10.6s515 / 244
CG-AL-X006hard1100.0 / 1003/3OK10.8s603 / 414
CG-AL-X007hard1100.0 / 1002/2OK1m 43s575 / 272
CG-AL-X008hard2100.0 / 1001/1OK10.8s2.5k / 3.8k
CG-AL-X009medium1100.0 / 1002/2OK10.8s493 / 198
CG-AL-X010medium1100.0 / 1003/3OK10.8s449 / 240
CG-AL-X011medium1100.0 / 1002/2OK10.9s557 / 214
CG-AL-X012hard1100.0 / 1001/1OK10.6s589 / 1.3k
CG-AL-X013hard1100.0 / 1002/2OK10.4s423 / 155
CG-AL-X014medium1100.0 / 1004/4OK10.7s458 / 141
CG-AL-X017medium2100.0 / 1003/3OK10.9s2.4k / 388
CG-AL-X018medium1100.0 / 1003/3OK11.1s606 / 300
CG-AL-X019medium2100.0 / 1003/3OK10.9s2.9k / 2.4k
CG-AL-X022medium2100.0 / 1003/3OK10.5s2.1k / 2.0k
CG-AL-X024medium1100.0 / 1003/3OK10.8s541 / 552
CG-AL-X025medium1100.0 / 1001/1OK10.8s601 / 533
CG-AL-X026medium1100.0 / 1003/3OK10.7s524 / 204
CG-AL-X027medium1100.0 / 1004/4OK10.5s424 / 367
CG-AL-X029medium1100.0 / 1002/2OK10.9s435 / 1.2k
CG-AL-X030medium1100.0 / 1002/2OK10.5s408 / 138
CG-AL-X031medium1100.0 / 1003/3OK10.6s465 / 202
CG-AL-X033hard1100.0 / 1002/2OK10.5s558 / 223
CG-AL-X034hard1100.0 / 1003/3OK10.9s486 / 286
CG-AL-X035hard262.5 / 1001/3OK11.1s1.4k / 2.0k
CG-AL-X037hard20.0 / 1000/0FAIL4.2s1.7k / 12k
CG-AL-X040hard20.0 / 1000/0FAIL4.2s2.4k / 4.7k
CG-AL-X041hard20.0 / 1000/0FAIL4.1s1.9k / 8.1k
CG-AL-X043hard20.0 / 1000/0FAIL4.0s2.5k / 13k
CG-AL-X044hard20.0 / 1000/0FAIL4.1s1.5k / 9.8k
CG-AL-X045hard2100.0 / 1003/3OK11.1s2.9k / 849
CG-AL-X046hard262.5 / 1000/2OK10.9s2.5k / 16k
CG-AL-X047hard20.0 / 1000/0FAIL3.9s2.3k / 12k
CG-AL-X050hard262.5 / 1000/2OK10.7s2.7k / 6.9k
CG-AL-X051hard262.5 / 1000/2OK10.6s2.0k / 947
CG-AL-X052hard1100.0 / 1003/3OK10.8s582 / 679
CG-AL-X055hard1100.0 / 1005/5OK10.6s546 / 423
CG-AL-X056hard2100.0 / 1005/5OK10.8s1.2k / 988
CG-AL-X057hard1100.0 / 1005/5OK10.8s411 / 474
CG-AL-X058hard1100.0 / 1005/5OK11.4s500 / 462
CG-AL-X059hard1100.0 / 1003/3OK10.5s511 / 121
CG-AL-X060hard1100.0 / 1003/3OK11.3s487 / 151
CG-AL-X061hard1100.0 / 1004/4OK10.6s572 / 191
CG-AL-X062hard2100.0 / 1004/4OK10.9s2.1k / 1.2k
CG-AL-X063hard1100.0 / 1003/3OK10.7s559 / 329
CG-AL-X064hard1100.0 / 1007/7OK10.5s457 / 379
CG-AL-X065hard1100.0 / 1006/6OK10.4s1.2k / 1.1k
CG-AL-X066hard1100.0 / 10014/14OK10.7s2.2k / 1.9k
CG-AL-X067hard20.0 / 1000/0FAIL4.3s2.8k / 39k
CG-AL-X068hard1100.0 / 10012/12OK10.8s1.9k / 5.6k
CG-AL-X069hard1100.0 / 1008/8OK10.8s1.9k / 2.1k
CG-AL-X070hard1100.0 / 10012/12OK10.7s1.9k / 1.5k
CG-AL-X071hard1100.0 / 1008/8OK10.6s2.2k / 1.9k
CG-AL-X072hard1100.0 / 1007/7OK10.6s2.1k / 1.7k
CG-AL-X073hard1100.0 / 1008/8OK10.5s2.5k / 2.3k
CG-AL-X074hard1100.0 / 1007/7OK10.8s2.6k / 12k
CG-AL-X075hard1100.0 / 1007/7OK11.1s1.4k / 5.0k
CG-AL-X076hard2100.0 / 10014/14OK11.0s5.9k / 33k
CG-AL-X077hard1100.0 / 10022/22OK10.7s2.6k / 2.3k
CG-AL-X078hard1100.0 / 10017/17OK11.1s2.0k / 1.6k
CG-AL-X079hard1100.0 / 10011/11OK11.2s2.0k / 3.3k
CG-AL-X080hard20.0 / 1000/0FAIL4.0s4.3k / 6.5k
CG-AL-X081hard1100.0 / 1008/8OK10.7s1.5k / 1.1k
CG-AL-X082hard1100.0 / 10015/15OK10.5s2.1k / 1.8k
CG-AL-X083hard1100.0 / 1009/9OK10.6s2.8k / 2.4k
CG-AL-X084hard1100.0 / 10010/10OK11.3s2.5k / 2.7k
CG-AL-X085hard1100.0 / 1007/7OK10.8s1.6k / 1.7k
CG-AL-X086hard262.5 / 1004/6OK10.6s6.9k / 20k
CG-AL-X087hard1100.0 / 1003/3OK10.9s1.8k / 2.2k
CG-AL-X088hard1100.0 / 1006/6OK10.8s1.7k / 2.5k
CG-AL-X089hard2100.0 / 10011/11OK11.2s4.0k / 14k
CG-AL-X090hard20.0 / 1000/0FAIL3.5s4.6k / 7.4k
CG-AL-X091hard1100.0 / 1006/6OK10.5s941 / 600
CG-AL-X092hard1100.0 / 10015/15OK10.9s716 / 353
CG-AL-X093hard1100.0 / 10010/10OK10.4s1.7k / 1.5k
CG-AL-X094hard1100.0 / 1007/7OK10.7s1.3k / 1.1k
CG-AL-X095hard1100.0 / 1005/5OK11.1s1.3k / 1.1k
CG-AL-X096hard1100.0 / 10049/49OK11.3s6.0k / 6.3k
CG-AL-X097hard1100.0 / 10046/46OK11.3s6.0k / 5.7k
CG-AL-X098hard1100.0 / 10029/29OK11.2s4.8k / 4.8k
CG-AL-X099hard1100.0 / 10039/39OK12.8s6.4k / 16k
CG-AL-X100hard1100.0 / 10035/35OK11.1s6.0k / 7.1k
CG-AL-X101hard1100.0 / 10010/10OK10.7s1.9k / 2.4k
CG-AL-X102hard2100.0 / 1008/8OK10.8s3.8k / 1.7k
CG-AL-X103hard1100.0 / 1007/7OK10.7s1.2k / 918
CG-AL-X104hard1100.0 / 1006/6OK10.8s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK11.1s1.3k / 872
CG-AL-X106hard1100.0 / 1005/5OK10.7s1.5k / 1.6k
CG-AL-X107hard1100.0 / 1004/4OK10.7s1.4k / 1.5k
CG-AL-X108hard1100.0 / 1006/6OK11.5s1.2k / 656
CG-AL-X109hard1100.0 / 1005/5OK11.2s916 / 494
CG-AL-X110hard1100.0 / 10017/17OK11.0s2.1k / 1.8k
CG-AL-X111hard1100.0 / 1008/8OK10.9s2.0k / 12k
CG-AL-X112hard262.5 / 10011/12OK11.3s3.6k / 6.9k
CG-AL-X113hard1100.0 / 10013/13OK10.8s1.3k / 2.4k
CG-AL-X114hard1100.0 / 1007/7OK10.6s1.2k / 932
CG-AL-X115hard2100.0 / 10013/13OK11.0s1.8k / 1.5k
CG-AL-X116hard1100.0 / 10017/17OK10.6s1.5k / 2.6k
CG-AL-X117hard1100.0 / 1008/8OK10.7s1.7k / 1.6k
CG-AL-X118hard1100.0 / 10017/17OK10.8s2.4k / 4.0k
CG-AL-X119hard2100.0 / 10015/15OK11.7s6.0k / 5.4k
CG-AL-X120hard1100.0 / 10012/12OK10.7s2.2k / 2.1k
CG-AL-X121hard1100.0 / 1006/6OK11.0s1.7k / 1.4k
CG-AL-X122hard1100.0 / 10010/10OK11.0s2.6k / 3.6k
CG-AL-X123hard1100.0 / 1005/5OK10.4s981 / 538
CG-AL-X124hard1100.0 / 10010/10OK10.7s1.7k / 1.8k
CG-AL-X125hard1100.0 / 1008/8OK11.0s2.3k / 5.1k
CG-AL-X126hard1100.0 / 10014/14OK10.4s1.2k / 1.7k
CG-AL-X127hard1100.0 / 1005/5OK11.6s1.1k / 848
CG-AL-X128hard1100.0 / 1008/8OK10.6s2.0k / 1.6k
CG-AL-X129hard1100.0 / 10014/14OK10.8s2.0k / 1.8k
CG-AL-X130hard2100.0 / 1005/5OK10.7s2.4k / 29k
CG-AL-X131hard1100.0 / 10013/13OK10.6s1.6k / 2.3k
CG-AL-X132hard1100.0 / 10010/10OK11.0s1.2k / 772
CG-AL-X133hard1100.0 / 1008/8OK11.0s2.8k / 26k
CG-AL-X134hard1100.0 / 1006/6OK10.9s2.0k / 2.2k
CG-AL-X135hard1100.0 / 1004/4OK10.7s1.4k / 1.0k
CG-AL-X136hard1100.0 / 1007/7OK11.1s1.2k / 1.1k
CG-AL-X137hard1100.0 / 1004/4OK10.5s1.5k / 3.0k
CG-AL-X138hard1100.0 / 1009/9OK11.4s2.4k / 2.6k
CG-AL-X139hard1100.0 / 10011/11OK11.5s2.8k / 2.7k
CG-AL-X140hard1100.0 / 1007/7OK11.1s2.5k / 20k
CG-AL-X141hard1100.0 / 10039/39OK11.9s6.1k / 8.7k
CG-AL-X142hard1100.0 / 10048/48OK11.8s6.8k / 26k
CG-AL-X143hard1100.0 / 10035/35OK15.8s7.2k / 7.4k
CG-AL-X144hard1100.0 / 10043/43OK11.4s6.4k / 6.8k
CG-AL-X145hard1100.0 / 10032/32OK11.6s7.4k / 7.6k
CG-AL-X146hard1100.0 / 1009/9OK10.9s2.9k / 14k
CG-AL-X147hard1100.0 / 1008/8OK10.8s2.2k / 1.9k
CG-AL-X148hard1100.0 / 1006/6OK10.5s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK10.8s1.9k / 1.6k
CG-AL-X150hard1100.0 / 1009/9OK11.6s3.2k / 14k
CG-AL-X151hard1100.0 / 1006/6OK11.6s1.4k / 972
CG-AL-X152hard1100.0 / 1008/8OK10.8s1.9k / 1.4k
CG-AL-X153hard1100.0 / 1009/9OK14.8s1.5k / 2.0k
CG-AL-X154hard1100.0 / 1009/9OK10.9s2.1k / 1.9k
CG-AL-X155hard1100.0 / 10011/11OK10.7s1.5k / 1.3k
CG-AL-X156hard1100.0 / 1007/7OK10.7s1.5k / 963
CG-AL-X157hard1100.0 / 10010/10OK10.8s2.2k / 1.7k
CG-AL-X158hard1100.0 / 1007/7OK10.8s1.3k / 798
CG-AL-X159hard1100.0 / 1007/7OK11.4s1.4k / 968
CG-AL-X160hard1100.0 / 10013/13OK11.3s2.0k / 2.0k
CG-AL-X161hard1100.0 / 10010/10OK11.0s2.4k / 2.5k
CG-AL-X162hard1100.0 / 1007/7OK11.0s1.6k / 1.3k
CG-AL-X163hard1100.0 / 1007/7OK10.9s1.7k / 1.4k
CG-AL-X164hard1100.0 / 1007/7OK10.9s1.5k / 1.6k
CG-AL-X165hard2100.0 / 10013/13OK13.5s11k / 32k
CG-AL-X166hard2100.0 / 10014/14OK11.9s6.8k / 4.7k
CG-AL-X167hard2100.0 / 10013/13OK11.2s6.4k / 23k
CG-AL-X168hard1100.0 / 1009/9OK12.5s2.2k / 6.6k
CG-AL-X169hard2100.0 / 10011/11OK11.7s7.0k / 22k
CG-AL-X170hard1100.0 / 10011/11OK11.9s5.2k / 7.5k
CG-AL-X171hard1100.0 / 1009/9OK11.1s2.5k / 9.1k
CG-AL-X172hard1100.0 / 10011/11OK11.1s3.8k / 14k
CG-AL-X173hard1100.0 / 10019/19OK12.4s5.4k / 27k
CG-AL-X174hard2100.0 / 10016/16OK11.4s15k / 14k
CG-AL-X185hard2100.0 / 10043/43OK11.3s12k / 6.3k
CG-AL-X187hard262.5 / 10030/33OK11.7s11k / 7.2k
CG-AL-X194hard262.5 / 10048/50OK12.0s18k / 16k
CG-AL-X211hard262.5 / 10039/43OK11.5s13k / 15k
CG-AL-X214hard2100.0 / 10034/34OK11.7s14k / 14k
CG-AL-X218hard2100.0 / 10027/27OK11.8s13k / 11k
CG-AL-X234hard2100.0 / 10035/35OK11.4s16k / 16k
CG-AL-X239hard2100.0 / 10037/37OK12.2s19k / 19k
CG-AL-X244hard2100.0 / 10038/38OK11.7s20k / 26k
CG-AL-X245hard2100.0 / 10063/63OK12.1s20k / 17k
CG-AL-X248hard2100.0 / 10066/66OK12.2s16k / 19k
CG-AL-X249hard2100.0 / 10037/37OK11.7s17k / 22k
CG-AL-X254hard2100.0 / 10070/70OK12.0s23k / 20k
CG-AL-X257hard20.0 / 1000/0FAIL0ms18k / 83k
CG-AL-X263hard2100.0 / 10061/61OK12.1s19k / 21k
CG-AL-X264hard262.5 / 10064/65OK11.8s22k / 29k
CG-AL-X270hard262.5 / 10059/63OK12.9s31k / 41k
CG-AL-X271hard262.5 / 10062/70OK12.7s28k / 24k
CG-AL-X272hard2100.0 / 10079/79OK12.0s23k / 29k
CG-AL-X274hard2100.0 / 10064/64OK12.8s23k / 21k
CG-AL-X276hard2100.0 / 10078/78OK12.7s24k / 37k
CG-AL-X278hard262.5 / 10068/71OK12.7s25k / 29k
CG-AL-X283hard2100.0 / 10076/76OK12.5s29k / 28k
CG-AL-X289hard2100.0 / 10057/57OK12.2s20k / 31k
CG-AL-X290hard2100.0 / 10047/47OK12.0s20k / 32k
CG-AL-X292hard20.0 / 1000/0FAIL3.7s21k / 31k
CG-AL-X293hard2100.0 / 10049/49OK11.9s18k / 19k
CG-AL-X296hard262.5 / 10046/47OK12.0s29k / 30k
CG-AL-X298hard262.5 / 10054/55OK11.9s16k / 31k