benchlm.ai

Claude 3.5 Sonnet vs DeepSeek-R1

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 35 (20 point difference).Claude 3.5 Sonnet wins 4 out of 4 categories.

Claude 3.5 Sonnet

CreatorAnthropic
TypeProprietary
Context200K
Score55

DeepSeek-R1

CreatorDeepSeek
TypeOpen Weight
Context128K
Score35

Knowledge

Claude 3.5 Sonnet

Claude 3.5 Sonnet

63.5

DeepSeek-R1

41.8

65
MMLU
44
65
GPQA
43
63
SuperGPQA
41
61
OpenBookQA
39

Coding

Claude 3.5 Sonnet

Claude 3.5 Sonnet

57

DeepSeek-R1

36

57
HumanEval
36

Mathematics

Claude 3.5 Sonnet

Claude 3.5 Sonnet

64

DeepSeek-R1

43

65
AIME 2023
44
67
AIME 2024
46
66
AIME 2025
45
61
HMMT Feb 2023
40
63
HMMT Feb 2024
42
62
HMMT Feb 2025
41
64
BRUMO 2025
43

Reasoning

Claude 3.5 Sonnet

Claude 3.5 Sonnet

62

DeepSeek-R1

41

63
SimpleQA
42
61
MuSR
40

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or DeepSeek-R1?

Claude 3.5 Sonnet scores higher overall with 55 vs 35, a difference of 20 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or DeepSeek-R1?

Claude 3.5 Sonnet leads in knowledge tasks with an average score of 63.5 vs 41.8.

Which is better for coding, Claude 3.5 Sonnet or DeepSeek-R1?

Claude 3.5 Sonnet leads in coding with an average score of 57 vs 36.

Which is better for math, Claude 3.5 Sonnet or DeepSeek-R1?

Claude 3.5 Sonnet leads in math with an average score of 64 vs 43.

Which is better for reasoning, Claude 3.5 Sonnet or DeepSeek-R1?

Claude 3.5 Sonnet leads in reasoning with an average score of 62 vs 41.

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