benchlm.ai

Claude 3.5 Sonnet vs GPT-4 Turbo

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

Quick Verdict

Claude 3.5 Sonnet wins overall with a score of 55 vs 50 (5 point difference).Claude 3.5 Sonnet wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

GPT-4 Turbo

CreatorOpenAI
TypeProprietary
Context128K
Score50

Knowledge

Claude 3.5 Sonnet

Claude 3.5 Sonnet

63.5

GPT-4 Turbo

58.5

65
MMLU
60
65
GPQA
60
63
SuperGPQA
58
61
OpenBookQA
56

Coding

Claude 3.5 Sonnet

Claude 3.5 Sonnet

57

GPT-4 Turbo

52

57
HumanEval
52

Mathematics

Claude 3.5 Sonnet

Claude 3.5 Sonnet

64

GPT-4 Turbo

59

65
AIME 2023
60
67
AIME 2024
62
66
AIME 2025
61
61
HMMT Feb 2023
56
63
HMMT Feb 2024
58
62
HMMT Feb 2025
57
64
BRUMO 2025
59

Reasoning

Claude 3.5 Sonnet

Claude 3.5 Sonnet

62

GPT-4 Turbo

57

63
SimpleQA
58
61
MuSR
56

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or GPT-4 Turbo?

Claude 3.5 Sonnet scores higher overall with 55 vs 50, a difference of 5 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or GPT-4 Turbo?

Claude 3.5 Sonnet leads in knowledge tasks with an average score of 63.5 vs 58.5.

Which is better for coding, Claude 3.5 Sonnet or GPT-4 Turbo?

Claude 3.5 Sonnet leads in coding with an average score of 57 vs 52.

Which is better for math, Claude 3.5 Sonnet or GPT-4 Turbo?

Claude 3.5 Sonnet leads in math with an average score of 64 vs 59.

Which is better for reasoning, Claude 3.5 Sonnet or GPT-4 Turbo?

Claude 3.5 Sonnet leads in reasoning with an average score of 62 vs 57.

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