benchlm.ai

Claude 3.5 Sonnet vs Claude Haiku 4.5

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

Quick Verdict

Claude Haiku 4.5 wins overall with a score of 57 vs 55 (2 point difference).Claude Haiku 4.5 wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

Claude Haiku 4.5

CreatorAnthropic
TypeProprietary
Context200K
Score57

Knowledge

Claude Haiku 4.5

Claude 3.5 Sonnet

63.5

Claude Haiku 4.5

65.8

65
MMLU
68
65
GPQA
67
63
SuperGPQA
65
61
OpenBookQA
63

Coding

Claude Haiku 4.5

Claude 3.5 Sonnet

57

Claude Haiku 4.5

60

57
HumanEval
60

Mathematics

Claude Haiku 4.5

Claude 3.5 Sonnet

64

Claude Haiku 4.5

67

65
AIME 2023
68
67
AIME 2024
70
66
AIME 2025
69
61
HMMT Feb 2023
64
63
HMMT Feb 2024
66
62
HMMT Feb 2025
65
64
BRUMO 2025
67

Reasoning

Claude Haiku 4.5

Claude 3.5 Sonnet

62

Claude Haiku 4.5

64

63
SimpleQA
65
61
MuSR
63

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or Claude Haiku 4.5?

Claude Haiku 4.5 scores higher overall with 57 vs 55, a difference of 2 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or Claude Haiku 4.5?

Claude Haiku 4.5 leads in knowledge tasks with an average score of 65.8 vs 63.5.

Which is better for coding, Claude 3.5 Sonnet or Claude Haiku 4.5?

Claude Haiku 4.5 leads in coding with an average score of 60 vs 57.

Which is better for math, Claude 3.5 Sonnet or Claude Haiku 4.5?

Claude Haiku 4.5 leads in math with an average score of 67 vs 64.

Which is better for reasoning, Claude 3.5 Sonnet or Claude Haiku 4.5?

Claude Haiku 4.5 leads in reasoning with an average score of 64 vs 62.

Related Comparisons

Claude 3.5 Sonnet vs GPT-5.4Claude 3.5 Sonnet vs Gemini 3.1 ProClaude 3.5 Sonnet vs Claude Opus 4.6Claude 3.5 Sonnet vs GPT-5.3 CodexClaude 3.5 Sonnet vs Grok 4.1Claude 3.5 Sonnet vs GPT-5.2