Claude 3 Haiku vs GPT-5.2

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

Quick Verdict

GPT-5.2 wins overall with a score of 83 vs 46 (37 point difference).GPT-5.2 wins 4 out of 4 categories.

Knowledge

GPT-5.2

Claude 3 Haiku

54.5

GPT-5.2

96

56
MMLU
99
56
GPQA
97
54
SuperGPQA
95
52
OpenBookQA
93

Coding

GPT-5.2

Claude 3 Haiku

48

GPT-5.2

91

48
HumanEval
91

Mathematics

GPT-5.2

Claude 3 Haiku

55

GPT-5.2

97.1

56
AIME 2023
99
58
AIME 2024
99
57
AIME 2025
98
52
HMMT Feb 2023
95
54
HMMT Feb 2024
97
53
HMMT Feb 2025
96
55
BRUMO 2025
96

Reasoning

GPT-5.2

Claude 3 Haiku

53

GPT-5.2

94

54
SimpleQA
95
52
MuSR
93

Frequently Asked Questions

Which is better, Claude 3 Haiku or GPT-5.2?

GPT-5.2 scores higher overall with 83 vs 46, a difference of 37 points across all benchmarks.

Which is better for knowledge tasks, Claude 3 Haiku or GPT-5.2?

GPT-5.2 leads in knowledge tasks with an average score of 96 vs 54.5.

Which is better for coding, Claude 3 Haiku or GPT-5.2?

GPT-5.2 leads in coding with an average score of 91 vs 48.

Which is better for math, Claude 3 Haiku or GPT-5.2?

GPT-5.2 leads in math with an average score of 97.1 vs 55.

Which is better for reasoning, Claude 3 Haiku or GPT-5.2?

GPT-5.2 leads in reasoning with an average score of 94 vs 53.