Claude 3.5 Sonnet vs DeepSeek LLM 2.0

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

Quick Verdict

DeepSeek LLM 2.0 wins overall with a score of 63 vs 55 (8 point difference).DeepSeek LLM 2.0 wins 4 out of 4 categories.

Knowledge

DeepSeek LLM 2.0

Claude 3.5 Sonnet

63.5

DeepSeek LLM 2.0

76.8

65
MMLU
79
65
GPQA
78
63
SuperGPQA
76
61
OpenBookQA
74

Coding

DeepSeek LLM 2.0

Claude 3.5 Sonnet

57

DeepSeek LLM 2.0

73

57
HumanEval
73

Mathematics

DeepSeek LLM 2.0

Claude 3.5 Sonnet

64

DeepSeek LLM 2.0

79

65
AIME 2023
80
67
AIME 2024
82
66
AIME 2025
81
61
HMMT Feb 2023
76
63
HMMT Feb 2024
78
62
HMMT Feb 2025
77
64
BRUMO 2025
79

Reasoning

DeepSeek LLM 2.0

Claude 3.5 Sonnet

62

DeepSeek LLM 2.0

76

63
SimpleQA
77
61
MuSR
75

Frequently Asked Questions

Which is better, Claude 3.5 Sonnet or DeepSeek LLM 2.0?

DeepSeek LLM 2.0 scores higher overall with 63 vs 55, a difference of 8 points across all benchmarks.

Which is better for knowledge tasks, Claude 3.5 Sonnet or DeepSeek LLM 2.0?

DeepSeek LLM 2.0 leads in knowledge tasks with an average score of 76.8 vs 63.5.

Which is better for coding, Claude 3.5 Sonnet or DeepSeek LLM 2.0?

DeepSeek LLM 2.0 leads in coding with an average score of 73 vs 57.

Which is better for math, Claude 3.5 Sonnet or DeepSeek LLM 2.0?

DeepSeek LLM 2.0 leads in math with an average score of 79 vs 64.

Which is better for reasoning, Claude 3.5 Sonnet or DeepSeek LLM 2.0?

DeepSeek LLM 2.0 leads in reasoning with an average score of 76 vs 62.