Claude Haiku 4.5 vs Mistral Large 2

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

Quick Verdict

Both models are tied with an overall score of 57.

Knowledge

Mistral Large 2

Claude Haiku 4.5

65.8

Mistral Large 2

66.5

68
MMLU
68
67
GPQA
68
65
SuperGPQA
66
63
OpenBookQA
64

Coding

Tie

Claude Haiku 4.5

60

Mistral Large 2

60

60
HumanEval
60

Mathematics

Tie

Claude Haiku 4.5

67

Mistral Large 2

67

68
AIME 2023
68
70
AIME 2024
70
69
AIME 2025
69
64
HMMT Feb 2023
64
66
HMMT Feb 2024
66
65
HMMT Feb 2025
65
67
BRUMO 2025
67

Reasoning

Mistral Large 2

Claude Haiku 4.5

64

Mistral Large 2

65

65
SimpleQA
66
63
MuSR
64

Frequently Asked Questions

Which is better, Claude Haiku 4.5 or Mistral Large 2?

Claude Haiku 4.5 and Mistral Large 2 are tied with identical overall scores of 57.

Which is better for knowledge tasks, Claude Haiku 4.5 or Mistral Large 2?

Mistral Large 2 leads in knowledge tasks with an average score of 66.5 vs 65.8.

Which is better for coding, Claude Haiku 4.5 or Mistral Large 2?

Claude Haiku 4.5 and Mistral Large 2 are tied for coding with average scores of 60.

Which is better for math, Claude Haiku 4.5 or Mistral Large 2?

Claude Haiku 4.5 and Mistral Large 2 are tied for math with average scores of 67.

Which is better for reasoning, Claude Haiku 4.5 or Mistral Large 2?

Mistral Large 2 leads in reasoning with an average score of 65 vs 64.