Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
GPT-OSS 120B wins overall with a score of 42 vs 20 (22 point difference).GPT-OSS 120B wins 4 out of 4 categories.
GPT-OSS 120B
48.8
Mistral 8x7B v0.2
26.8
GPT-OSS 120B
43
Mistral 8x7B v0.2
21
GPT-OSS 120B
50
Mistral 8x7B v0.2
28
GPT-OSS 120B
48
Mistral 8x7B v0.2
26
GPT-OSS 120B scores higher overall with 42 vs 20, a difference of 22 points across all benchmarks.
GPT-OSS 120B leads in knowledge tasks with an average score of 48.8 vs 26.8.
GPT-OSS 120B leads in coding with an average score of 43 vs 21.
GPT-OSS 120B leads in math with an average score of 50 vs 28.
GPT-OSS 120B leads in reasoning with an average score of 48 vs 26.