CodeSOTAβOriginal site ↗
← BoolQ / sub-1B cohort

Completed / CodeSOTA execution on White

Inspect the measurement.

SlayerLab/Slayer149-Balanced-ARC-E-ft-v2 · BoolQ · 62.5% accuracy

32-example pilot. Sub-1B 32-example pilot; FP32, 1024-token input ceiling, mean answer-token log likelihood. Native masked-padding adapter uses unpadded row forwards. Compare only this cohort protocol.
Run ID / completed
3ce0ba3d66280b6cbd47845b
17 Oct 2026, 01:09 UTC
Model revision
7d11e8fd63764baf00c276f586b2aa776648ed33
Comparison scope
bea6197d37b7692e8660c09f3be4bdc84c65bd6d240a6e23f418cc1d58d63ca5
Evaluator SHA-256
5011da874931804d8f5159762d18d33b71feb02044d808b106cca5da28178509
Observed resources
2s elapsed · 0.92 GiB peak torch allocation
Dollar cost: not measured

Download evidence

Example-level outputs

All 32 scored examples. Ground truth and model predictions are preserved in the downloadable JSONL.

{"choices":["no","yes"],"id":"0","log_likelihood_mean":[-3.014932632446289,-3.2218494415283203],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"1","log_likelihood_mean":[-3.6527230739593506,-4.262408256530762],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"2","log_likelihood_mean":[-4.154003143310547,-4.854629039764404],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"3","log_likelihood_mean":[-3.420778751373291,-2.0927815437316895],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"4","log_likelihood_mean":[-7.122030258178711,-7.083946228027344],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"5","log_likelihood_mean":[-4.209578514099121,-3.076216220855713],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"6","log_likelihood_mean":[-2.4542617797851562,-2.7290573120117188],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"7","log_likelihood_mean":[-3.4985969066619873,-4.079773902893066],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"8","log_likelihood_mean":[-2.835761308670044,-2.3039772510528564],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"9","log_likelihood_mean":[-3.6475934982299805,-3.9443206787109375],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"10","log_likelihood_mean":[-3.4633069038391113,-2.319817066192627],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"11","log_likelihood_mean":[-3.6976675987243652,-3.0034050941467285],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"12","log_likelihood_mean":[-4.0435590744018555,-3.2066903114318848],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"13","log_likelihood_mean":[-4.336574554443359,-2.736995220184326],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"14","log_likelihood_mean":[-4.207502365112305,-2.12048077583313],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"15","log_likelihood_mean":[-4.16583776473999,-3.301252841949463],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"16","log_likelihood_mean":[-4.480509281158447,-3.8498687744140625],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"17","log_likelihood_mean":[-4.058383941650391,-2.6002705097198486],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"18","log_likelihood_mean":[-4.078700065612793,-3.0537333488464355],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"19","log_likelihood_mean":[-3.742906093597412,-3.7248473167419434],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"20","log_likelihood_mean":[-2.6914405822753906,-2.745452880859375],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"21","log_likelihood_mean":[-2.665022134780884,-2.8191168308258057],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"22","log_likelihood_mean":[-2.733121871948242,-3.577861785888672],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"23","log_likelihood_mean":[-2.805955648422241,-3.5038440227508545],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"24","log_likelihood_mean":[-4.162164688110352,-4.08277702331543],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"25","log_likelihood_mean":[-3.0823073387145996,-1.4547076225280762],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"26","log_likelihood_mean":[-2.8985934257507324,-2.795332431793213],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"27","log_likelihood_mean":[-3.768897294998169,-3.0804316997528076],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"28","log_likelihood_mean":[-4.278165817260742,-2.569563150405884],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"29","log_likelihood_mean":[-4.5029425621032715,-2.6381406784057617],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"30","log_likelihood_mean":[-3.4594202041625977,-3.4661855697631836],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"31","log_likelihood_mean":[-2.9569294452667236,-1.6267244815826416],"prediction":1,"reference":1,"score":1.0}