CodeSOTAβOriginal site ↗
← Natural language inference

Completed / CodeSOTA execution on White

Inspect the measurement.

Qwen/Qwen2.5-0.5B · SNLI · 37.5% accuracy

32-example pilot. Pilot subset, custom CodeSOTA protocol. Not an official full-benchmark score.
Run ID / completed
272e772751322114921d9ee6
16 Oct 2026, 23:25 UTC
Model revision
060db6499f32faf8b98477b0a26969ef7d8b9987
Comparison scope
38bbd002f19fa172682f143fb1299a09e00b6693591f1fb8d9d938db1f26f0b7
Evaluator SHA-256
a71a6c0fe0c3cc3f1694659595be1112cfc36eb190be5ff6e0a3380105415b3e
Observed resources
2s elapsed · 0.95 GiB peak torch allocation
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":[-6.18819522857666,-14.537675857543945,-7.112871170043945],"prediction":0,"reference":1,"score":0.0,"seconds":0.13153662800323218}
{"choices":["entailment","neutral","contradiction"],"id":"1","log_likelihood_mean":[-5.934259414672852,-15.492379188537598,-10.304879188537598],"prediction":0,"reference":0,"score":1.0,"seconds":0.026772012002766132}
{"choices":["entailment","neutral","contradiction"],"id":"2","log_likelihood_mean":[-5.268342018127441,-10.826041221618652,-7.6932291984558105],"prediction":0,"reference":2,"score":0.0,"seconds":0.025389223010279238}
{"choices":["entailment","neutral","contradiction"],"id":"3","log_likelihood_mean":[-4.238788604736328,-10.410652160644531,-9.742683410644531],"prediction":0,"reference":1,"score":0.0,"seconds":0.02539767907001078}
{"choices":["entailment","neutral","contradiction"],"id":"4","log_likelihood_mean":[-3.3481619358062744,-10.417856216430664,-9.445199966430664],"prediction":0,"reference":0,"score":1.0,"seconds":0.025795590947382152}
{"choices":["entailment","neutral","contradiction"],"id":"5","log_likelihood_mean":[-3.7499001026153564,-10.780424118041992,-9.030424118041992],"prediction":0,"reference":2,"score":0.0,"seconds":0.025289647979661822}
{"choices":["entailment","neutral","contradiction"],"id":"6","log_likelihood_mean":[-4.262263298034668,-8.347569465637207,-9.941319465637207],"prediction":0,"reference":0,"score":1.0,"seconds":0.028993605985306203}
{"choices":["entailment","neutral","contradiction"],"id":"7","log_likelihood_mean":[-3.465062379837036,-8.407176971435547,-9.957958221435547],"prediction":0,"reference":1,"score":0.0,"seconds":0.025531118037179112}
{"choices":["entailment","neutral","contradiction"],"id":"8","log_likelihood_mean":[-3.5814900398254395,-8.578327178955078,-9.304889678955078],"prediction":0,"reference":2,"score":0.0,"seconds":0.02546715794596821}
{"choices":["entailment","neutral","contradiction"],"id":"9","log_likelihood_mean":[-3.6619248390197754,-9.161567687988281,-7.005317687988281],"prediction":0,"reference":1,"score":0.0,"seconds":0.025622828979976475}
{"choices":["entailment","neutral","contradiction"],"id":"10","log_likelihood_mean":[-3.1174633502960205,-10.31752872467041,-8.20424747467041],"prediction":0,"reference":0,"score":1.0,"seconds":0.026408124016597867}
{"choices":["entailment","neutral","contradiction"],"id":"11","log_likelihood_mean":[-3.111159563064575,-10.152782440185547,-7.582469940185547],"prediction":0,"reference":2,"score":0.0,"seconds":0.027994631906040013}
{"choices":["entailment","neutral","contradiction"],"id":"12","log_likelihood_mean":[-2.7753822803497314,-8.583507537841797,-8.259288787841797],"prediction":0,"reference":0,"score":1.0,"seconds":0.025938987964764237}
{"choices":["entailment","neutral","contradiction"],"id":"13","log_likelihood_mean":[-3.5880377292633057,-8.939637184143066,-8.763855934143066],"prediction":0,"reference":0,"score":1.0,"seconds":0.025669215014204383}
{"choices":["entailment","neutral","contradiction"],"id":"14","log_likelihood_mean":[-3.249009847640991,-7.499307632446289,-5.843057632446289],"prediction":0,"reference":2,"score":0.0,"seconds":0.025575020001269877}
{"choices":["entailment","neutral","contradiction"],"id":"15","log_likelihood_mean":[-3.7583799362182617,-8.847609519958496,-4.824172019958496],"prediction":0,"reference":2,"score":0.0,"seconds":0.02540018397849053}
{"choices":["entailment","neutral","contradiction"],"id":"16","log_likelihood_mean":[-4.219577789306641,-11.221014976501465,-9.029608726501465],"prediction":0,"reference":0,"score":1.0,"seconds":0.02544947504065931}
{"choices":["entailment","neutral","contradiction"],"id":"17","log_likelihood_mean":[-4.027932167053223,-11.352486610412598,-7.0634236335754395],"prediction":0,"reference":1,"score":0.0,"seconds":0.025253440020605922}
{"choices":["entailment","neutral","contradiction"],"id":"18","log_likelihood_mean":[-3.543391466140747,-11.062259674072266,-11.698978424072266],"prediction":0,"reference":0,"score":1.0,"seconds":0.025378262042067945}
{"choices":["entailment","neutral","contradiction"],"id":"19","log_likelihood_mean":[-4.196258068084717,-9.481403350830078,-10.868122100830078],"prediction":0,"reference":2,"score":0.0,"seconds":0.025288415024988353}
{"choices":["entailment","neutral","contradiction"],"id":"20","log_likelihood_mean":[-2.455395460128784,-10.496160507202148,-10.300848007202148],"prediction":0,"reference":1,"score":0.0,"seconds":0.027703410014510155}
{"choices":["entailment","neutral","contradiction"],"id":"21","log_likelihood_mean":[-3.0540413856506348,-9.040754318237305,-10.618879318237305],"prediction":0,"reference":2,"score":0.0,"seconds":0.025809467071667314}
{"choices":["entailment","neutral","contradiction"],"id":"22","log_likelihood_mean":[-3.2568161487579346,-9.906682968139648,-13.396917343139648],"prediction":0,"reference":0,"score":1.0,"seconds":0.025423287064768374}
{"choices":["entailment","neutral","contradiction"],"id":"23","log_likelihood_mean":[-3.7448840141296387,-10.605340957641602,-11.296747207641602],"prediction":0,"reference":1,"score":0.0,"seconds":0.025367403053678572}
{"choices":["entailment","neutral","contradiction"],"id":"24","log_likelihood_mean":[-3.3001797199249268,-11.377801895141602,-10.043817520141602],"prediction":0,"reference":1,"score":0.0,"seconds":0.025384453940205276}
{"choices":["entailment","neutral","contradiction"],"id":"25","log_likelihood_mean":[-4.012823581695557,-12.128098487854004,-9.460129737854004],"prediction":0,"reference":2,"score":0.0,"seconds":0.02655146096367389}
{"choices":["entailment","neutral","contradiction"],"id":"26","log_likelihood_mean":[-2.9428627490997314,-11.675474166870117,-9.370786666870117],"prediction":0,"reference":0,"score":1.0,"seconds":0.02541832788847387}
{"choices":["entailment","neutral","contradiction"],"id":"27","log_likelihood_mean":[-2.8251824378967285,-8.765745162963867,-9.793088912963867],"prediction":0,"reference":0,"score":1.0,"seconds":0.025834804982878268}
{"choices":["entailment","neutral","contradiction"],"id":"28","log_likelihood_mean":[-3.4403929710388184,-8.748432159423828,-10.529682159423828],"prediction":0,"reference":1,"score":0.0,"seconds":0.027205710997805}
{"choices":["entailment","neutral","contradiction"],"id":"29","log_likelihood_mean":[-4.231813430786133,-8.687518119812012,-7.664080619812012],"prediction":0,"reference":2,"score":0.0,"seconds":0.02602522901725024}
{"choices":["entailment","neutral","contradiction"],"id":"30","log_likelihood_mean":[-3.9275553226470947,-6.601663589477539,-8.125101089477539],"prediction":0,"reference":2,"score":0.0,"seconds":0.028771552024409175}
{"choices":["entailment","neutral","contradiction"],"id":"31","log_likelihood_mean":[-3.841325044631958,-7.107034206390381,-9.275003433227539],"prediction":0,"reference":0,"score":1.0,"seconds":0.025845765019766986}