Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Moonshot v1 wins overall with a score of 44 vs 20 (24 point difference).Moonshot v1 wins 4 out of 4 categories.
Mistral 8x7B v0.2
26.8
Moonshot v1
50.8
Mistral 8x7B v0.2
21
Moonshot v1
45
Mistral 8x7B v0.2
28
Moonshot v1
52
Mistral 8x7B v0.2
26
Moonshot v1
50
Moonshot v1 scores higher overall with 44 vs 20, a difference of 24 points across all benchmarks.
Moonshot v1 leads in knowledge tasks with an average score of 50.8 vs 26.8.
Moonshot v1 leads in coding with an average score of 45 vs 21.
Moonshot v1 leads in math with an average score of 52 vs 28.
Moonshot v1 leads in reasoning with an average score of 50 vs 26.