Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Mistral Large 2 wins overall with a score of 57 vs 24 (33 point difference).Mistral Large 2 wins 4 out of 4 categories.
DeepSeek V3.1
30.8
Mistral Large 2
66.5
DeepSeek V3.1
25
Mistral Large 2
60
DeepSeek V3.1
32
Mistral Large 2
67
DeepSeek V3.1
30
Mistral Large 2
65
Mistral Large 2 scores higher overall with 57 vs 24, a difference of 33 points across all benchmarks.
Mistral Large 2 leads in knowledge tasks with an average score of 66.5 vs 30.8.
Mistral Large 2 leads in coding with an average score of 60 vs 25.
Mistral Large 2 leads in math with an average score of 67 vs 32.
Mistral Large 2 leads in reasoning with an average score of 65 vs 30.