Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-OSS 120B wins overall with a score of 42 vs 41 (1 point difference).GPT-OSS 120B wins 4 out of 4 categories.
Gemini 2.5 Flash
47.8
GPT-OSS 120B
48.8
Gemini 2.5 Flash
42
GPT-OSS 120B
43
Gemini 2.5 Flash
49
GPT-OSS 120B
50
Gemini 2.5 Flash
47
GPT-OSS 120B
48
GPT-OSS 120B scores higher overall with 42 vs 41, a difference of 1 points across all benchmarks.
GPT-OSS 120B leads in knowledge tasks with an average score of 48.8 vs 47.8.
GPT-OSS 120B leads in coding with an average score of 43 vs 42.
GPT-OSS 120B leads in math with an average score of 50 vs 49.
GPT-OSS 120B leads in reasoning with an average score of 48 vs 47.