Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Developer Knowledge Evaluation on DevEval

61Win Rate

gpt-oss-120b (high)

-0.3615.5731.547.43Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
618.828.24
2026.06
398.368.48
2026.06
328.178.67
2026.06
227.598.75
2026.06
176.828.86
2026.06
35.999.11
2026.06
25.39.15