Completed / CodeSOTA execution on White
Inspect the measurement.
Qwen/Qwen2.5-0.5B-Instruct · BoolQ · 71.9% 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
141ceb6c09dc8f0156f70c0c
17 Oct 2026, 01:08 UTC
17 Oct 2026, 01:08 UTC
Model revision
7ae557604adf67be50417f59c2c2f167def9a775Comparison scope
bea6197d37b7692e8660c09f3be4bdc84c65bd6d240a6e23f418cc1d58d63ca5Evaluator SHA-256
5011da874931804d8f5159762d18d33b71feb02044d808b106cca5da28178509Observed resources
2s elapsed · 2.19 GiB peak torch allocation
Dollar cost: not measured
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":[-2.6902008056640625,-1.1748350858688354],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"1","log_likelihood_mean":[-2.315357208251953,-4.391807556152344],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"2","log_likelihood_mean":[-5.540864944458008,-2.8222694396972656],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"3","log_likelihood_mean":[-5.710590362548828,-0.3347185552120209],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"4","log_likelihood_mean":[-4.180236339569092,-6.987258434295654],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"5","log_likelihood_mean":[-1.8240511417388916,-5.772456169128418],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"6","log_likelihood_mean":[-3.5221409797668457,-4.3985066413879395],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"7","log_likelihood_mean":[-4.018311023712158,-1.6953186988830566],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"8","log_likelihood_mean":[-3.9102306365966797,-4.496978759765625],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"9","log_likelihood_mean":[-3.759094476699829,-2.5675318241119385],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"10","log_likelihood_mean":[-3.1553516387939453,-3.4649782180786133],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"11","log_likelihood_mean":[-2.7976231575012207,-3.6092543601989746],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"12","log_likelihood_mean":[-3.0180842876434326,-4.615461349487305],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"13","log_likelihood_mean":[-3.604896068572998,-1.262433409690857],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"14","log_likelihood_mean":[-4.044435501098633,-0.3819272816181183],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"15","log_likelihood_mean":[-3.6907083988189697,-1.8640272617340088],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"16","log_likelihood_mean":[-3.379535675048828,-1.5742321014404297],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"17","log_likelihood_mean":[-2.3589963912963867,-0.8663567304611206],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"18","log_likelihood_mean":[-1.981278896331787,-0.7847418785095215],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"19","log_likelihood_mean":[-3.584902763366699,-1.0672215223312378],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"20","log_likelihood_mean":[-3.7188000679016113,-5.082746982574463],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"21","log_likelihood_mean":[-3.846196174621582,-1.7052621841430664],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"22","log_likelihood_mean":[-2.3602657318115234,-2.0984086990356445],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"23","log_likelihood_mean":[-3.940413475036621,-2.600865364074707],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"24","log_likelihood_mean":[-3.9163479804992676,-4.244424343109131],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"25","log_likelihood_mean":[-4.360694408416748,-2.4136195182800293],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"26","log_likelihood_mean":[-3.0251705646514893,-4.226179122924805],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"27","log_likelihood_mean":[-2.3336360454559326,-2.701998472213745],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"28","log_likelihood_mean":[-2.073305130004883,-1.1830710172653198],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"29","log_likelihood_mean":[-3.5865626335144043,-2.598874568939209],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"30","log_likelihood_mean":[-5.6551923751831055,-2.4041757583618164],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"31","log_likelihood_mean":[-3.5897653102874756,-2.6691949367523193],"prediction":1,"reference":1,"score":1.0}