Completed / CodeSOTA execution on White
Inspect the measurement.
Qwen/Qwen2.5-0.5B · BoolQ · 68.8% accuracy
32-example pilot. Pilot subset, CodeSOTA batched-v2 execution. Separate scope from serial v1; unchanged prompt/tokenization/metric contracts.
Run ID / completed
ff345349801249c15997d2a6
17 Oct 2026, 00:49 UTC
17 Oct 2026, 00:49 UTC
Model revision
060db6499f32faf8b98477b0a26969ef7d8b9987Comparison scope
50f1e323d677230fdcedb032817fe2f0387aab1b8fc6c2b0f2282f32d4318845Evaluator SHA-256
bc899fb160f6881408863cd8bcdf96102dd6d8b10559a5f781a8cd816103da77Observed resources
1s elapsed · 1.10 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":[-3.8339014053344727,-3.2948389053344727],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"1","log_likelihood_mean":[-1.2411484718322754,-1.3817734718322754],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"2","log_likelihood_mean":[-4.114293575286865,-2.2158560752868652],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"3","log_likelihood_mean":[-3.2705295085906982,-0.450217068195343],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"4","log_likelihood_mean":[-0.949837327003479,-1.856087327003479],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"5","log_likelihood_mean":[-0.8538073897361755,-2.1038074493408203],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"6","log_likelihood_mean":[-0.9441840648651123,-1.7723090648651123],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"7","log_likelihood_mean":[-1.3336997032165527,-1.1149497032165527],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"8","log_likelihood_mean":[-1.4356828927993774,-1.9513078927993774],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"9","log_likelihood_mean":[-2.2042908668518066,-1.1261659860610962],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"10","log_likelihood_mean":[-2.02382230758667,-1.1488221883773804],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"11","log_likelihood_mean":[-1.2313809394836426,-1.2938809394836426],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"12","log_likelihood_mean":[-0.966805100440979,-2.1386799812316895],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"13","log_likelihood_mean":[-2.3887691497802734,-0.7012690901756287],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"14","log_likelihood_mean":[-2.3352560997009277,-1.0227562189102173],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"15","log_likelihood_mean":[-1.5778392553329468,-1.1715892553329468],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"16","log_likelihood_mean":[-1.5369372367858887,-1.1775622367858887],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"17","log_likelihood_mean":[-1.6055282354354858,-0.8086532354354858],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"18","log_likelihood_mean":[-1.626746416091919,-0.9861214756965637],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"19","log_likelihood_mean":[-2.1189160346984863,-0.7595409154891968],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"20","log_likelihood_mean":[-1.1458770036697388,-1.4583770036697388],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"21","log_likelihood_mean":[-2.5328288078308105,-1.2672038078308105],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"22","log_likelihood_mean":[-1.0307526588439941,-1.2182526588439941],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"23","log_likelihood_mean":[-2.418455123901367,-1.0278301239013672],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"24","log_likelihood_mean":[-1.3759535551071167,-1.5322035551071167],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"25","log_likelihood_mean":[-2.2552313804626465,-0.6771064400672913],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"26","log_likelihood_mean":[-0.95339035987854,-1.31276535987854],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"27","log_likelihood_mean":[-1.8020679950714111,-1.7239429950714111],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"28","log_likelihood_mean":[-1.4502149820327759,-0.8877149820327759],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"29","log_likelihood_mean":[-1.485722303390503,-1.001347303390503],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"30","log_likelihood_mean":[-1.8844850063323975,-0.8844849467277527],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"31","log_likelihood_mean":[-2.03582763671875,-1.2858275175094604],"prediction":1,"reference":1,"score":1.0}