GPT-4 Turbo vs Moonshot v1

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

Quick Verdict

GPT-4 Turbo wins overall with a score of 50 vs 44 (6 point difference).GPT-4 Turbo wins 4 out of 4 categories.

Knowledge

GPT-4 Turbo

GPT-4 Turbo

58.5

Moonshot v1

50.8

60
MMLU
53
60
GPQA
52
58
SuperGPQA
50
56
OpenBookQA
48

Coding

GPT-4 Turbo

GPT-4 Turbo

52

Moonshot v1

45

52
HumanEval
45

Mathematics

GPT-4 Turbo

GPT-4 Turbo

59

Moonshot v1

52

60
AIME 2023
53
62
AIME 2024
55
61
AIME 2025
54
56
HMMT Feb 2023
49
58
HMMT Feb 2024
51
57
HMMT Feb 2025
50
59
BRUMO 2025
52

Reasoning

GPT-4 Turbo

GPT-4 Turbo

57

Moonshot v1

50

58
SimpleQA
51
56
MuSR
49

Frequently Asked Questions

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

GPT-4 Turbo scores higher overall with 50 vs 44, a difference of 6 points across all benchmarks.

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

GPT-4 Turbo leads in knowledge tasks with an average score of 58.5 vs 50.8.

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

GPT-4 Turbo leads in coding with an average score of 52 vs 45.

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

GPT-4 Turbo leads in math with an average score of 59 vs 52.

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

GPT-4 Turbo leads in reasoning with an average score of 57 vs 50.