Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
DeepSeek Coder 2.0 wins overall with a score of 64 vs 52 (12 point difference).DeepSeek Coder 2.0 wins 4 out of 4 categories.
DeepSeek Coder 2.0
77.8
Mistral 8x7B
62.8
DeepSeek Coder 2.0
82
Mistral 8x7B
55
DeepSeek Coder 2.0
80
Mistral 8x7B
64
DeepSeek Coder 2.0
77
Mistral 8x7B
62
DeepSeek Coder 2.0 scores higher overall with 64 vs 52, a difference of 12 points across all benchmarks.
DeepSeek Coder 2.0 leads in knowledge tasks with an average score of 77.8 vs 62.8.
DeepSeek Coder 2.0 leads in coding with an average score of 82 vs 55.
DeepSeek Coder 2.0 leads in math with an average score of 80 vs 64.
DeepSeek Coder 2.0 leads in reasoning with an average score of 77 vs 62.