Claude Haiku 4.5 Benchmark Scores & Performance

Benchmark analysis of Claude Haiku 4.5 by Anthropic across 14 tests.

Creator

Anthropic

Source Type

Proprietary

Reasoning

Non-Reasoning

Context Window

200K

Overall Score

57#48 of 88

Knowledge Benchmarks

MMLU
68
GPQA
67
SuperGPQA
65
OpenBookQA
63

Coding Benchmarks

HumanEval
60

Mathematics Benchmarks

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

Reasoning Benchmarks

SimpleQA
65
MuSR
63

Frequently Asked Questions

How does Claude Haiku 4.5 perform overall in AI benchmarks?

Claude Haiku 4.5 ranks #48 out of 88 models with an overall score of 57. It is created by Anthropic and features a 200K context window.

Is Claude Haiku 4.5 good for knowledge and understanding?

Claude Haiku 4.5 ranks #48 out of 88 models in knowledge and understanding benchmarks with an average score of 65.8. There are stronger options in this category.

Is Claude Haiku 4.5 good for coding and programming?

Claude Haiku 4.5 ranks #48 out of 88 models in coding and programming benchmarks with an average score of 60. There are stronger options in this category.

Is Claude Haiku 4.5 good for mathematics?

Claude Haiku 4.5 ranks #48 out of 88 models in mathematics benchmarks with an average score of 67. There are stronger options in this category.

Is Claude Haiku 4.5 good for reasoning and logic?

Claude Haiku 4.5 ranks #48 out of 88 models in reasoning and logic benchmarks with an average score of 64. There are stronger options in this category.

What is the context window size of Claude Haiku 4.5?

Claude Haiku 4.5 has a context window of 200K tokens, which determines how much text it can process in a single interaction.