Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Moonshot v1 wins overall with a score of 44 vs 36 (8 point difference).Moonshot v1 wins 4 out of 4 categories.
Gemma 3 27B
42.8
Moonshot v1
50.8
Gemma 3 27B
37
Moonshot v1
45
Gemma 3 27B
44
Moonshot v1
52
Gemma 3 27B
42
Moonshot v1
50
Moonshot v1 scores higher overall with 44 vs 36, a difference of 8 points across all benchmarks.
Moonshot v1 leads in knowledge tasks with an average score of 50.8 vs 42.8.
Moonshot v1 leads in coding with an average score of 45 vs 37.
Moonshot v1 leads in math with an average score of 52 vs 44.
Moonshot v1 leads in reasoning with an average score of 50 vs 42.