Completed / CodeSOTA execution on White
Inspect the measurement.
Qwen/Qwen2.5-1.5B · SNLI · 37.5% accuracy
32-example pilot. Pilot subset, CodeSOTA batched-v2 execution. Separate scope from serial v1; unchanged prompt/tokenization/metric contracts.
Run ID / completed
bddd3154bd9cf23f3dece3fb
17 Oct 2026, 00:48 UTC
17 Oct 2026, 00:48 UTC
Model revision
8faed761d45a263340a0528343f099c05c9a4323Comparison scope
3ef5086324e4a200ffa81c1058aab801250aedfad5e4f11c7c4b8a63c1bf5b3eEvaluator SHA-256
bc899fb160f6881408863cd8bcdf96102dd6d8b10559a5f781a8cd816103da77Observed resources
2s elapsed · 2.93 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":["entailment","neutral","contradiction"],"id":"0","log_likelihood_mean":[-7.016393184661865,-14.157195091247559,-14.985320091247559],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"1","log_likelihood_mean":[-5.8400373458862305,-12.075312614440918,-15.472935676574707],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"2","log_likelihood_mean":[-5.743255615234375,-9.698873519897461,-13.026998519897461],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"3","log_likelihood_mean":[-5.292688846588135,-12.145174980163574,-15.285799980163574],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"4","log_likelihood_mean":[-4.665380954742432,-10.930508613586426,-15.547696113586426],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"5","log_likelihood_mean":[-4.204537868499756,-12.032811164855957,-11.689061164855957],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"6","log_likelihood_mean":[-3.740335464477539,-9.59492301940918,-13.24336051940918],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"7","log_likelihood_mean":[-5.097269535064697,-8.31372356414795,-13.34497356414795],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"8","log_likelihood_mean":[-4.2245683670043945,-7.659461498260498,-12.02664852142334],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"9","log_likelihood_mean":[-4.315158843994141,-8.359468460083008,-9.054780960083008],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"10","log_likelihood_mean":[-5.479727268218994,-9.65858268737793,-13.13514518737793],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"11","log_likelihood_mean":[-5.166884422302246,-9.155516624450684,-10.960204124450684],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"12","log_likelihood_mean":[-4.735020160675049,-9.781855583190918,-13.305293083190918],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"13","log_likelihood_mean":[-3.6633832454681396,-8.373858451843262,-11.553545951843262],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"14","log_likelihood_mean":[-3.8696115016937256,-6.918132781982422,-6.723846912384033],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"15","log_likelihood_mean":[-4.698010444641113,-7.599247455596924,-7.656188011169434],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"16","log_likelihood_mean":[-3.775270938873291,-8.714879989624023,-12.113317489624023],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"17","log_likelihood_mean":[-5.079791069030762,-11.161945343017578,-16.240070343017578],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"18","log_likelihood_mean":[-4.726853847503662,-9.868430137634277,-13.915305137634277],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"19","log_likelihood_mean":[-3.936436653137207,-6.483554840087891,-9.45230484008789],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"20","log_likelihood_mean":[-4.5764617919921875,-8.558931350708008,-12.957368850708008],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"21","log_likelihood_mean":[-5.0226874351501465,-10.507976531982422,-12.804851531982422],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"22","log_likelihood_mean":[-3.8775837421417236,-8.971357345581055,-13.151044845581055],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"23","log_likelihood_mean":[-4.042683124542236,-8.222609519958496,-10.746047019958496],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"24","log_likelihood_mean":[-4.677450180053711,-9.796337127685547,-14.718212127685547],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"25","log_likelihood_mean":[-4.095620632171631,-7.468845844268799,-11.609471321105957],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"26","log_likelihood_mean":[-5.3158440589904785,-10.97532844543457,-16.28782844543457],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"27","log_likelihood_mean":[-3.761279582977295,-9.262470245361328,-12.856220245361328],"prediction":0,"reference":0,"score":1.0}
{"choices":["entailment","neutral","contradiction"],"id":"28","log_likelihood_mean":[-4.741650581359863,-11.7648286819458,-14.4874849319458],"prediction":0,"reference":1,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"29","log_likelihood_mean":[-4.035122871398926,-8.389655113220215,-9.959967613220215],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"30","log_likelihood_mean":[-5.219449043273926,-8.700446128845215,-10.575446128845215],"prediction":0,"reference":2,"score":0.0}
{"choices":["entailment","neutral","contradiction"],"id":"31","log_likelihood_mean":[-5.134313583374023,-9.336849212646484,-13.180599212646484],"prediction":0,"reference":0,"score":1.0}