Completed / CodeSOTA execution on White
Inspect the measurement.
Qwen/Qwen2.5-1.5B · SNLI · 37.5% accuracy
32-example pilot. Pilot subset, custom CodeSOTA protocol. Not an official full-benchmark score.
Run ID / completed
5a2a497f01a1e75965c07849
16 Oct 2026, 23:30 UTC
16 Oct 2026, 23:30 UTC
Model revision
8faed761d45a263340a0528343f099c05c9a4323Comparison scope
38bbd002f19fa172682f143fb1299a09e00b6693591f1fb8d9d938db1f26f0b7Evaluator SHA-256
a71a6c0fe0c3cc3f1694659595be1112cfc36eb190be5ff6e0a3380105415b3eObserved resources
2s elapsed · 2.90 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":[-7.050454616546631,-14.187037467956543,-15.030787467956543],"prediction":0,"reference":1,"score":0.0,"seconds":0.11979690694715828}
{"choices":["entailment","neutral","contradiction"],"id":"1","log_likelihood_mean":[-5.853798866271973,-12.105244636535645,-15.488057136535645],"prediction":0,"reference":0,"score":1.0,"seconds":0.029026787029579282}
{"choices":["entailment","neutral","contradiction"],"id":"2","log_likelihood_mean":[-5.707408428192139,-9.645155906677246,-12.934218406677246],"prediction":0,"reference":2,"score":0.0,"seconds":0.032905120053328574}
{"choices":["entailment","neutral","contradiction"],"id":"3","log_likelihood_mean":[-5.272735595703125,-12.179612159729004,-15.296799659729004],"prediction":0,"reference":1,"score":0.0,"seconds":0.03761560493148863}
{"choices":["entailment","neutral","contradiction"],"id":"4","log_likelihood_mean":[-4.653532028198242,-10.961908340454102,-15.590814590454102],"prediction":0,"reference":0,"score":1.0,"seconds":0.02897642191965133}
{"choices":["entailment","neutral","contradiction"],"id":"5","log_likelihood_mean":[-4.222958087921143,-12.101552963256836,-11.796865463256836],"prediction":0,"reference":2,"score":0.0,"seconds":0.028810503077693284}
{"choices":["entailment","neutral","contradiction"],"id":"6","log_likelihood_mean":[-3.7319581508636475,-9.59807014465332,-13.25432014465332],"prediction":0,"reference":0,"score":1.0,"seconds":0.03268351696897298}
{"choices":["entailment","neutral","contradiction"],"id":"7","log_likelihood_mean":[-5.0871758460998535,-8.318957328796387,-13.365832328796387],"prediction":0,"reference":1,"score":0.0,"seconds":0.028864394058473408}
{"choices":["entailment","neutral","contradiction"],"id":"8","log_likelihood_mean":[-4.190928936004639,-7.65045166015625,-11.98638916015625],"prediction":0,"reference":2,"score":0.0,"seconds":0.029784910031594336}
{"choices":["entailment","neutral","contradiction"],"id":"9","log_likelihood_mean":[-4.362420082092285,-8.334463119506836,-9.014150619506836],"prediction":0,"reference":1,"score":0.0,"seconds":0.028865654952824116}
{"choices":["entailment","neutral","contradiction"],"id":"10","log_likelihood_mean":[-5.483163356781006,-9.60028076171875,-13.06121826171875],"prediction":0,"reference":0,"score":1.0,"seconds":0.033151288982480764}
{"choices":["entailment","neutral","contradiction"],"id":"11","log_likelihood_mean":[-5.166780948638916,-9.152717590332031,-10.941780090332031],"prediction":0,"reference":2,"score":0.0,"seconds":0.0311108740279451}
{"choices":["entailment","neutral","contradiction"],"id":"12","log_likelihood_mean":[-4.737015247344971,-9.831543922424316,-13.409668922424316],"prediction":0,"reference":0,"score":1.0,"seconds":0.02995420596562326}
{"choices":["entailment","neutral","contradiction"],"id":"13","log_likelihood_mean":[-3.628532648086548,-8.380516052246094,-11.552391052246094],"prediction":0,"reference":0,"score":1.0,"seconds":0.030529469018802047}
{"choices":["entailment","neutral","contradiction"],"id":"14","log_likelihood_mean":[-3.8544423580169678,-6.9164018630981445,-6.7367143630981445],"prediction":0,"reference":2,"score":0.0,"seconds":0.03393666399642825}
{"choices":["entailment","neutral","contradiction"],"id":"15","log_likelihood_mean":[-4.704770088195801,-7.590843200683594,-7.614280700683594],"prediction":0,"reference":2,"score":0.0,"seconds":0.030144791933707893}
{"choices":["entailment","neutral","contradiction"],"id":"16","log_likelihood_mean":[-3.7792062759399414,-8.713518142700195,-12.151018142700195],"prediction":0,"reference":0,"score":1.0,"seconds":0.02982848195824772}
{"choices":["entailment","neutral","contradiction"],"id":"17","log_likelihood_mean":[-5.104677200317383,-11.177728652954102,-16.2285099029541],"prediction":0,"reference":1,"score":0.0,"seconds":0.029823502991348505}
{"choices":["entailment","neutral","contradiction"],"id":"18","log_likelihood_mean":[-4.713466167449951,-9.876001358032227,-13.930688858032227],"prediction":0,"reference":0,"score":1.0,"seconds":0.031976568046957254}
{"choices":["entailment","neutral","contradiction"],"id":"19","log_likelihood_mean":[-3.9204115867614746,-6.4736552238464355,-9.434593200683594],"prediction":0,"reference":2,"score":0.0,"seconds":0.02900191000662744}
{"choices":["entailment","neutral","contradiction"],"id":"20","log_likelihood_mean":[-4.587250709533691,-8.58231258392334,-12.96512508392334],"prediction":0,"reference":1,"score":0.0,"seconds":0.029975014040246606}
{"choices":["entailment","neutral","contradiction"],"id":"21","log_likelihood_mean":[-4.974826812744141,-10.499078750610352,-12.827203750610352],"prediction":0,"reference":2,"score":0.0,"seconds":0.029495351016521454}
{"choices":["entailment","neutral","contradiction"],"id":"22","log_likelihood_mean":[-3.892251491546631,-8.96053409576416,-13.10897159576416],"prediction":0,"reference":0,"score":1.0,"seconds":0.03291882504709065}
{"choices":["entailment","neutral","contradiction"],"id":"23","log_likelihood_mean":[-4.0512309074401855,-8.195785522460938,-10.672348022460938],"prediction":0,"reference":1,"score":0.0,"seconds":0.02933327795471996}
{"choices":["entailment","neutral","contradiction"],"id":"24","log_likelihood_mean":[-4.682398796081543,-9.816764831542969,-14.715202331542969],"prediction":0,"reference":1,"score":0.0,"seconds":0.02895754703786224}
{"choices":["entailment","neutral","contradiction"],"id":"25","log_likelihood_mean":[-4.0884785652160645,-7.433199882507324,-11.526949882507324],"prediction":0,"reference":2,"score":0.0,"seconds":0.02969943091738969}
{"choices":["entailment","neutral","contradiction"],"id":"26","log_likelihood_mean":[-5.302048206329346,-10.974032402038574,-16.321687698364258],"prediction":0,"reference":0,"score":1.0,"seconds":0.03193765599280596}
{"choices":["entailment","neutral","contradiction"],"id":"27","log_likelihood_mean":[-3.7526144981384277,-9.235493659973145,-12.797993659973145],"prediction":0,"reference":0,"score":1.0,"seconds":0.03240018803626299}
{"choices":["entailment","neutral","contradiction"],"id":"28","log_likelihood_mean":[-4.7235870361328125,-11.776811599731445,-14.468217849731445],"prediction":0,"reference":1,"score":0.0,"seconds":0.02981691004242748}
{"choices":["entailment","neutral","contradiction"],"id":"29","log_likelihood_mean":[-4.020721435546875,-8.384584426879883,-9.939271926879883],"prediction":0,"reference":2,"score":0.0,"seconds":0.02966143994126469}
{"choices":["entailment","neutral","contradiction"],"id":"30","log_likelihood_mean":[-5.188634395599365,-8.648238182067871,-10.531050682067871],"prediction":0,"reference":2,"score":0.0,"seconds":0.029701314051635563}
{"choices":["entailment","neutral","contradiction"],"id":"31","log_likelihood_mean":[-5.145448207855225,-9.31040096282959,-13.13071346282959],"prediction":0,"reference":0,"score":1.0,"seconds":0.03295404091477394}