DeepSeek V3.1 (Reasoning) vs Gemini 1.0 Pro

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

Quick Verdict

Gemini 1.0 Pro wins overall with a score of 52 vs 25 (27 point difference).Gemini 1.0 Pro wins 4 out of 4 categories.

Knowledge

Gemini 1.0 Pro

DeepSeek V3.1 (Reasoning)

31.8

Gemini 1.0 Pro

60.5

34
MMLU
62
33
GPQA
62
31
SuperGPQA
60
29
OpenBookQA
58

Coding

Gemini 1.0 Pro

DeepSeek V3.1 (Reasoning)

26

Gemini 1.0 Pro

54

26
HumanEval
54

Mathematics

Gemini 1.0 Pro

DeepSeek V3.1 (Reasoning)

33

Gemini 1.0 Pro

61

34
AIME 2023
62
36
AIME 2024
64
35
AIME 2025
63
30
HMMT Feb 2023
58
32
HMMT Feb 2024
60
31
HMMT Feb 2025
59
33
BRUMO 2025
61

Reasoning

Gemini 1.0 Pro

DeepSeek V3.1 (Reasoning)

31

Gemini 1.0 Pro

59

32
SimpleQA
60
30
MuSR
58

Frequently Asked Questions

Which is better, DeepSeek V3.1 (Reasoning) or Gemini 1.0 Pro?

Gemini 1.0 Pro scores higher overall with 52 vs 25, a difference of 27 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 (Reasoning) or Gemini 1.0 Pro?

Gemini 1.0 Pro leads in knowledge tasks with an average score of 60.5 vs 31.8.

Which is better for coding, DeepSeek V3.1 (Reasoning) or Gemini 1.0 Pro?

Gemini 1.0 Pro leads in coding with an average score of 54 vs 26.

Which is better for math, DeepSeek V3.1 (Reasoning) or Gemini 1.0 Pro?

Gemini 1.0 Pro leads in math with an average score of 61 vs 33.

Which is better for reasoning, DeepSeek V3.1 (Reasoning) or Gemini 1.0 Pro?

Gemini 1.0 Pro leads in reasoning with an average score of 59 vs 31.