benchlm.ai

Claude Opus 4.6 vs Claude Sonnet 4.5

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

Quick Verdict

Claude Opus 4.6 wins overall with a score of 86 vs 74 (12 point difference).Claude Opus 4.6 wins 4 out of 4 categories.

Claude Opus 4.6

CreatorAnthropic
TypeProprietary
Context1M
Score86

Claude Sonnet 4.5

CreatorAnthropic
TypeProprietary
Context1M
Score74

Knowledge

Claude Opus 4.6

Claude Opus 4.6

96

Claude Sonnet 4.5

92

99
MMLU
95
97
GPQA
93
95
SuperGPQA
91
93
OpenBookQA
89

Coding

Claude Opus 4.6

Claude Opus 4.6

91

Claude Sonnet 4.5

87

91
HumanEval
87

Mathematics

Claude Opus 4.6

Claude Opus 4.6

97.1

Claude Sonnet 4.5

96

99
AIME 2023
97
99
AIME 2024
99
98
AIME 2025
98
95
HMMT Feb 2023
93
97
HMMT Feb 2024
95
96
HMMT Feb 2025
94
96
BRUMO 2025
96

Reasoning

Claude Opus 4.6

Claude Opus 4.6

94

Claude Sonnet 4.5

90

95
SimpleQA
91
93
MuSR
89

Frequently Asked Questions

Which is better, Claude Opus 4.6 or Claude Sonnet 4.5?

Claude Opus 4.6 scores higher overall with 86 vs 74, a difference of 12 points across all benchmarks.

Which is better for knowledge tasks, Claude Opus 4.6 or Claude Sonnet 4.5?

Claude Opus 4.6 leads in knowledge tasks with an average score of 96 vs 92.

Which is better for coding, Claude Opus 4.6 or Claude Sonnet 4.5?

Claude Opus 4.6 leads in coding with an average score of 91 vs 87.

Which is better for math, Claude Opus 4.6 or Claude Sonnet 4.5?

Claude Opus 4.6 leads in math with an average score of 97.1 vs 96.

Which is better for reasoning, Claude Opus 4.6 or Claude Sonnet 4.5?

Claude Opus 4.6 leads in reasoning with an average score of 94 vs 90.

Related Comparisons

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