Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-OSS 120B wins overall with a score of 42 vs 31 (11 point difference).GPT-OSS 120B wins 4 out of 4 categories.
GPT-OSS 120B
48.8
Qwen3 235B 2507 (Reasoning)
37.8
GPT-OSS 120B
43
Qwen3 235B 2507 (Reasoning)
32
GPT-OSS 120B
50
Qwen3 235B 2507 (Reasoning)
39
GPT-OSS 120B
48
Qwen3 235B 2507 (Reasoning)
37
GPT-OSS 120B scores higher overall with 42 vs 31, a difference of 11 points across all benchmarks.
GPT-OSS 120B leads in knowledge tasks with an average score of 48.8 vs 37.8.
GPT-OSS 120B leads in coding with an average score of 43 vs 32.
GPT-OSS 120B leads in math with an average score of 50 vs 39.
GPT-OSS 120B leads in reasoning with an average score of 48 vs 37.