benchlm.ai

Claude Haiku 4.5 vs GPT-5.4

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

Quick Verdict

GPT-5.4 wins overall with a score of 88 vs 57 (31 point difference).GPT-5.4 wins 4 out of 4 categories.

Claude Haiku 4.5

CreatorAnthropic
TypeProprietary
Context200K
Score57

GPT-5.4

CreatorOpenAI
TypeProprietary
Context1M
Score88

Knowledge

GPT-5.4

Claude Haiku 4.5

65.8

GPT-5.4

96

68
MMLU
99
67
GPQA
97
65
SuperGPQA
95
63
OpenBookQA
93

Coding

GPT-5.4

Claude Haiku 4.5

60

GPT-5.4

91

60
HumanEval
91

Mathematics

GPT-5.4

Claude Haiku 4.5

67

GPT-5.4

97.1

68
AIME 2023
99
70
AIME 2024
99
69
AIME 2025
98
64
HMMT Feb 2023
95
66
HMMT Feb 2024
97
65
HMMT Feb 2025
96
67
BRUMO 2025
96

Reasoning

GPT-5.4

Claude Haiku 4.5

64

GPT-5.4

94

65
SimpleQA
95
63
MuSR
93

Frequently Asked Questions

Which is better, Claude Haiku 4.5 or GPT-5.4?

GPT-5.4 scores higher overall with 88 vs 57, a difference of 31 points across all benchmarks.

Which is better for knowledge tasks, Claude Haiku 4.5 or GPT-5.4?

GPT-5.4 leads in knowledge tasks with an average score of 96 vs 65.8.

Which is better for coding, Claude Haiku 4.5 or GPT-5.4?

GPT-5.4 leads in coding with an average score of 91 vs 60.

Which is better for math, Claude Haiku 4.5 or GPT-5.4?

GPT-5.4 leads in math with an average score of 97.1 vs 67.

Which is better for reasoning, Claude Haiku 4.5 or GPT-5.4?

GPT-5.4 leads in reasoning with an average score of 94 vs 64.

Related Comparisons

Claude Haiku 4.5 vs Gemini 3.1 ProClaude Haiku 4.5 vs Claude Opus 4.6Claude Haiku 4.5 vs GPT-5.3 CodexClaude Haiku 4.5 vs Grok 4.1Claude Haiku 4.5 vs GPT-5.2Claude Haiku 4.5 vs GPT-5.2-Codex