Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Mistral 8x7B wins overall with a score of 52 vs 42 (10 point difference).Mistral 8x7B wins 4 out of 4 categories.
GPT-OSS 120B
48.8
Mistral 8x7B
62.8
GPT-OSS 120B
43
Mistral 8x7B
55
GPT-OSS 120B
50
Mistral 8x7B
64
GPT-OSS 120B
48
Mistral 8x7B
62
Mistral 8x7B scores higher overall with 52 vs 42, a difference of 10 points across all benchmarks.
Mistral 8x7B leads in knowledge tasks with an average score of 62.8 vs 48.8.
Mistral 8x7B leads in coding with an average score of 55 vs 43.
Mistral 8x7B leads in math with an average score of 64 vs 50.
Mistral 8x7B leads in reasoning with an average score of 62 vs 48.