benchlm.ai

Claude 3.5 Sonnet vs Claude 4.1 Opus

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

Quick Verdict

Claude 4.1 Opus wins overall with a score of 61 vs 55 (6 point difference).Claude 4.1 Opus wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

Claude 4.1 Opus

CreatorAnthropic
TypeProprietary
Context200K
Score61

Knowledge

Claude 4.1 Opus

Claude 3.5 Sonnet

63.5

Claude 4.1 Opus

74.5

65
MMLU
76
65
GPQA
76
63
SuperGPQA
74
61
OpenBookQA
72

Coding

Claude 4.1 Opus

Claude 3.5 Sonnet

57

Claude 4.1 Opus

68

57
HumanEval
68

Mathematics

Claude 4.1 Opus

Claude 3.5 Sonnet

64

Claude 4.1 Opus

75

65
AIME 2023
76
67
AIME 2024
78
66
AIME 2025
77
61
HMMT Feb 2023
72
63
HMMT Feb 2024
74
62
HMMT Feb 2025
73
64
BRUMO 2025
75

Reasoning

Claude 4.1 Opus

Claude 3.5 Sonnet

62

Claude 4.1 Opus

73

63
SimpleQA
74
61
MuSR
72

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or Claude 4.1 Opus?

Claude 4.1 Opus scores higher overall with 61 vs 55, a difference of 6 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or Claude 4.1 Opus?

Claude 4.1 Opus leads in knowledge tasks with an average score of 74.5 vs 63.5.

Which is better for coding, Claude 3.5 Sonnet or Claude 4.1 Opus?

Claude 4.1 Opus leads in coding with an average score of 68 vs 57.

Which is better for math, Claude 3.5 Sonnet or Claude 4.1 Opus?

Claude 4.1 Opus leads in math with an average score of 75 vs 64.

Which is better for reasoning, Claude 3.5 Sonnet or Claude 4.1 Opus?

Claude 4.1 Opus leads in reasoning with an average score of 73 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