Claude 3.5 Sonnet vs DeepSeek V3.1 (Reasoning)

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 25 (30 point difference).Claude 3.5 Sonnet wins 4 out of 4 categories.

Knowledge

Claude 3.5 Sonnet

Claude 3.5 Sonnet

63.5

DeepSeek V3.1 (Reasoning)

31.8

65
MMLU
34
65
GPQA
33
63
SuperGPQA
31
61
OpenBookQA
29

Coding

Claude 3.5 Sonnet

Claude 3.5 Sonnet

57

DeepSeek V3.1 (Reasoning)

26

57
HumanEval
26

Mathematics

Claude 3.5 Sonnet

Claude 3.5 Sonnet

64

DeepSeek V3.1 (Reasoning)

33

65
AIME 2023
34
67
AIME 2024
36
66
AIME 2025
35
61
HMMT Feb 2023
30
63
HMMT Feb 2024
32
62
HMMT Feb 2025
31
64
BRUMO 2025
33

Reasoning

Claude 3.5 Sonnet

Claude 3.5 Sonnet

62

DeepSeek V3.1 (Reasoning)

31

63
SimpleQA
32
61
MuSR
30

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or DeepSeek V3.1 (Reasoning)?

Claude 3.5 Sonnet scores higher overall with 55 vs 25, a difference of 30 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or DeepSeek V3.1 (Reasoning)?

Claude 3.5 Sonnet leads in knowledge tasks with an average score of 63.5 vs 31.8.

Which is better for coding, Claude 3.5 Sonnet or DeepSeek V3.1 (Reasoning)?

Claude 3.5 Sonnet leads in coding with an average score of 57 vs 26.

Which is better for math, Claude 3.5 Sonnet or DeepSeek V3.1 (Reasoning)?

Claude 3.5 Sonnet leads in math with an average score of 64 vs 33.

Which is better for reasoning, Claude 3.5 Sonnet or DeepSeek V3.1 (Reasoning)?

Claude 3.5 Sonnet leads in reasoning with an average score of 62 vs 31.