Completed / CodeSOTA execution on White
Inspect the measurement.
SlayerLab/Slayer139-1.01 · BoolQ · 56.3% 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
a64f0553519f2724df9f01c1
17 Oct 2026, 01:12 UTC
17 Oct 2026, 01:12 UTC
Model revision
2e72c696d7c5cad73dc58606b0751b911dc94495Comparison scope
bea6197d37b7692e8660c09f3be4bdc84c65bd6d240a6e23f418cc1d58d63ca5Evaluator SHA-256
5011da874931804d8f5159762d18d33b71feb02044d808b106cca5da28178509Observed resources
2s elapsed · 0.87 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":[-4.084885597229004,-4.858173847198486],"prediction":0,"reference":0,"score":1.0}
{"choices":["no","yes"],"id":"1","log_likelihood_mean":[-5.22224235534668,-4.366454124450684],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"2","log_likelihood_mean":[-4.460685729980469,-6.206126689910889],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"3","log_likelihood_mean":[-2.471494197845459,-2.1270899772644043],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"4","log_likelihood_mean":[-4.732741832733154,-5.328445911407471],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"5","log_likelihood_mean":[-3.281214475631714,-1.8394219875335693],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"6","log_likelihood_mean":[-2.3200502395629883,-2.6712684631347656],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"7","log_likelihood_mean":[-2.46574068069458,-3.4914450645446777],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"8","log_likelihood_mean":[-2.9098362922668457,-2.229337692260742],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"9","log_likelihood_mean":[-3.007159471511841,-1.8680717945098877],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"10","log_likelihood_mean":[-2.5525455474853516,-2.0703177452087402],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"11","log_likelihood_mean":[-4.5306620597839355,-3.8416905403137207],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"12","log_likelihood_mean":[-3.7993931770324707,-2.674771308898926],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"13","log_likelihood_mean":[-3.5059127807617188,-3.9091124534606934],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"14","log_likelihood_mean":[-4.013896942138672,-2.7420828342437744],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"15","log_likelihood_mean":[-2.597627878189087,-2.2207400798797607],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"16","log_likelihood_mean":[-5.537227630615234,-4.051419258117676],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"17","log_likelihood_mean":[-3.4761264324188232,-1.795762300491333],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"18","log_likelihood_mean":[-3.2430295944213867,-2.3075828552246094],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"19","log_likelihood_mean":[-2.5058088302612305,-2.9001612663269043],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"20","log_likelihood_mean":[-3.287126302719116,-2.883258104324341],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"21","log_likelihood_mean":[-3.035277843475342,-3.3841991424560547],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"22","log_likelihood_mean":[-3.3625245094299316,-2.380469799041748],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"23","log_likelihood_mean":[-2.3132028579711914,-3.3613152503967285],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"24","log_likelihood_mean":[-2.8099892139434814,-3.080068349838257],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"25","log_likelihood_mean":[-3.2015750408172607,-2.199793577194214],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"26","log_likelihood_mean":[-3.3557636737823486,-3.9582479000091553],"prediction":0,"reference":1,"score":0.0}
{"choices":["no","yes"],"id":"27","log_likelihood_mean":[-3.2546582221984863,-2.6842689514160156],"prediction":1,"reference":0,"score":0.0}
{"choices":["no","yes"],"id":"28","log_likelihood_mean":[-3.0552399158477783,-2.4833872318267822],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"29","log_likelihood_mean":[-3.1336259841918945,-2.0744428634643555],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"30","log_likelihood_mean":[-3.0015358924865723,-2.947150230407715],"prediction":1,"reference":1,"score":1.0}
{"choices":["no","yes"],"id":"31","log_likelihood_mean":[-3.0295164585113525,-2.4184410572052],"prediction":1,"reference":1,"score":1.0}