benchlm.ai

DeepSeek V3.1 vs Gemini 3 Flash

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

Quick Verdict

Gemini 3 Flash wins overall with a score of 58 vs 24 (34 point difference).Gemini 3 Flash wins 4 out of 4 categories.

DeepSeek V3.1

CreatorDeepSeek
TypeOpen Weight
Context128K
Score24

Gemini 3 Flash

CreatorGoogle
TypeProprietary
Context1M
Score58

Knowledge

Gemini 3 Flash

DeepSeek V3.1

30.8

Gemini 3 Flash

67.8

33
MMLU
70
32
GPQA
69
30
SuperGPQA
67
28
OpenBookQA
65

Coding

Gemini 3 Flash

DeepSeek V3.1

25

Gemini 3 Flash

62

25
HumanEval
62

Mathematics

Gemini 3 Flash

DeepSeek V3.1

32

Gemini 3 Flash

69

33
AIME 2023
70
35
AIME 2024
72
34
AIME 2025
71
29
HMMT Feb 2023
66
31
HMMT Feb 2024
68
30
HMMT Feb 2025
67
32
BRUMO 2025
69

Reasoning

Gemini 3 Flash

DeepSeek V3.1

30

Gemini 3 Flash

66

31
SimpleQA
67
29
MuSR
65

Frequently Asked Questions

Which is better, DeepSeek V3.1 or Gemini 3 Flash?

Gemini 3 Flash scores higher overall with 58 vs 24, a difference of 34 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.1 or Gemini 3 Flash?

Gemini 3 Flash leads in knowledge tasks with an average score of 67.8 vs 30.8.

Which is better for coding, DeepSeek V3.1 or Gemini 3 Flash?

Gemini 3 Flash leads in coding with an average score of 62 vs 25.

Which is better for math, DeepSeek V3.1 or Gemini 3 Flash?

Gemini 3 Flash leads in math with an average score of 69 vs 32.

Which is better for reasoning, DeepSeek V3.1 or Gemini 3 Flash?

Gemini 3 Flash leads in reasoning with an average score of 66 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