Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Both models are tied with an overall score of 52.
Gemini 1.0 Pro
60.5
Mistral 8x7B
62.8
Gemini 1.0 Pro
54
Mistral 8x7B
55
Gemini 1.0 Pro
61
Mistral 8x7B
64
Gemini 1.0 Pro
59
Mistral 8x7B
62
Gemini 1.0 Pro and Mistral 8x7B are tied with identical overall scores of 52.
Mistral 8x7B leads in knowledge tasks with an average score of 62.8 vs 60.5.
Mistral 8x7B leads in coding with an average score of 55 vs 54.
Mistral 8x7B leads in math with an average score of 64 vs 61.
Mistral 8x7B leads in reasoning with an average score of 62 vs 59.