GPT-4o vs Moonshot v1

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

Quick Verdict

GPT-4o wins overall with a score of 56 vs 44 (12 point difference).GPT-4o wins 4 out of 4 categories.

Knowledge

GPT-4o

GPT-4o

64.5

Moonshot v1

50.8

66
MMLU
53
66
GPQA
52
64
SuperGPQA
50
62
OpenBookQA
48

Coding

GPT-4o

GPT-4o

58

Moonshot v1

45

58
HumanEval
45

Mathematics

GPT-4o

GPT-4o

65

Moonshot v1

52

66
AIME 2023
53
68
AIME 2024
55
67
AIME 2025
54
62
HMMT Feb 2023
49
64
HMMT Feb 2024
51
63
HMMT Feb 2025
50
65
BRUMO 2025
52

Reasoning

GPT-4o

GPT-4o

63

Moonshot v1

50

64
SimpleQA
51
62
MuSR
49

Frequently Asked Questions

Which is better, GPT-4o or Moonshot v1?

GPT-4o scores higher overall with 56 vs 44, a difference of 12 points across all benchmarks.

Which is better for knowledge tasks, GPT-4o or Moonshot v1?

GPT-4o leads in knowledge tasks with an average score of 64.5 vs 50.8.

Which is better for coding, GPT-4o or Moonshot v1?

GPT-4o leads in coding with an average score of 58 vs 45.

Which is better for math, GPT-4o or Moonshot v1?

GPT-4o leads in math with an average score of 65 vs 52.

Which is better for reasoning, GPT-4o or Moonshot v1?

GPT-4o leads in reasoning with an average score of 63 vs 50.