benchlm.ai

DeepSeek V3.1 vs Gemini 1.5 Pro

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

Quick Verdict

Gemini 1.5 Pro wins overall with a score of 54 vs 24 (30 point difference).Gemini 1.5 Pro wins 4 out of 4 categories.

DeepSeek V3.1

CreatorDeepSeek
TypeOpen Weight
Context128K
Score24

Gemini 1.5 Pro

CreatorGoogle
TypeProprietary
Context2M
Score54

Knowledge

Gemini 1.5 Pro

DeepSeek V3.1

30.8

Gemini 1.5 Pro

62.5

33
MMLU
64
32
GPQA
64
30
SuperGPQA
62
28
OpenBookQA
60

Coding

Gemini 1.5 Pro

DeepSeek V3.1

25

Gemini 1.5 Pro

56

25
HumanEval
56

Mathematics

Gemini 1.5 Pro

DeepSeek V3.1

32

Gemini 1.5 Pro

63

33
AIME 2023
64
35
AIME 2024
66
34
AIME 2025
65
29
HMMT Feb 2023
60
31
HMMT Feb 2024
62
30
HMMT Feb 2025
61
32
BRUMO 2025
63

Reasoning

Gemini 1.5 Pro

DeepSeek V3.1

30

Gemini 1.5 Pro

61

31
SimpleQA
62
29
MuSR
60

Frequently Asked Questions

Which is better, DeepSeek V3.1 or Gemini 1.5 Pro?

Gemini 1.5 Pro scores higher overall with 54 vs 24, a difference of 30 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 or Gemini 1.5 Pro?

Gemini 1.5 Pro leads in knowledge tasks with an average score of 62.5 vs 30.8.

Which is better for coding, DeepSeek V3.1 or Gemini 1.5 Pro?

Gemini 1.5 Pro leads in coding with an average score of 56 vs 25.

Which is better for math, DeepSeek V3.1 or Gemini 1.5 Pro?

Gemini 1.5 Pro leads in math with an average score of 63 vs 32.

Which is better for reasoning, DeepSeek V3.1 or Gemini 1.5 Pro?

Gemini 1.5 Pro leads in reasoning with an average score of 61 vs 30.

Related Comparisons

DeepSeek V3.1 vs GPT-5.4DeepSeek V3.1 vs Gemini 3.1 ProDeepSeek V3.1 vs Claude Opus 4.6DeepSeek V3.1 vs GPT-5.3 CodexDeepSeek V3.1 vs Grok 4.1DeepSeek V3.1 vs GPT-5.2