Llama 3.1 405B vs Moonshot v1

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Llama 3.1 405B wins overall with a score of 58 vs 44 (14 point difference).Llama 3.1 405B wins 4 out of 4 categories.

Knowledge

Llama 3.1 405B

Llama 3.1 405B

68.5

Moonshot v1

50.8

70
MMLU
53
70
GPQA
52
68
SuperGPQA
50
66
OpenBookQA
48

Coding

Llama 3.1 405B

Llama 3.1 405B

62

Moonshot v1

45

62
HumanEval
45

Mathematics

Llama 3.1 405B

Llama 3.1 405B

69

Moonshot v1

52

70
AIME 2023
53
72
AIME 2024
55
71
AIME 2025
54
66
HMMT Feb 2023
49
68
HMMT Feb 2024
51
67
HMMT Feb 2025
50
69
BRUMO 2025
52

Reasoning

Llama 3.1 405B

Llama 3.1 405B

67

Moonshot v1

50

68
SimpleQA
51
66
MuSR
49

Frequently Asked Questions

Which is better, Llama 3.1 405B or Moonshot v1?

Llama 3.1 405B scores higher overall with 58 vs 44, a difference of 14 points across all benchmarks.

Which is better for knowledge tasks, Llama 3.1 405B or Moonshot v1?

Llama 3.1 405B leads in knowledge tasks with an average score of 68.5 vs 50.8.

Which is better for coding, Llama 3.1 405B or Moonshot v1?

Llama 3.1 405B leads in coding with an average score of 62 vs 45.

Which is better for math, Llama 3.1 405B or Moonshot v1?

Llama 3.1 405B leads in math with an average score of 69 vs 52.

Which is better for reasoning, Llama 3.1 405B or Moonshot v1?

Llama 3.1 405B leads in reasoning with an average score of 67 vs 50.