benchlm.ai

DeepSeekMath V2 vs Gemini 3.1 Pro

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

Quick Verdict

Gemini 3.1 Pro wins overall with a score of 87 vs 64 (23 point difference).Gemini 3.1 Pro wins 4 out of 4 categories.

DeepSeekMath V2

CreatorDeepSeek
TypeOpen Weight
Context128K
Score64

Gemini 3.1 Pro

CreatorGoogle
TypeProprietary
Context1M
Score87

Knowledge

Gemini 3.1 Pro

DeepSeekMath V2

77.8

Gemini 3.1 Pro

96

80
MMLU
99
79
GPQA
97
77
SuperGPQA
95
75
OpenBookQA
93

Coding

Gemini 3.1 Pro

DeepSeekMath V2

72

Gemini 3.1 Pro

91

72
HumanEval
91

Mathematics

Gemini 3.1 Pro

DeepSeekMath V2

79

Gemini 3.1 Pro

97.1

80
AIME 2023
99
82
AIME 2024
99
81
AIME 2025
98
76
HMMT Feb 2023
95
78
HMMT Feb 2024
97
77
HMMT Feb 2025
96
79
BRUMO 2025
96

Reasoning

Gemini 3.1 Pro

DeepSeekMath V2

76

Gemini 3.1 Pro

94

77
SimpleQA
95
75
MuSR
93

Frequently Asked Questions

Which is better, DeepSeekMath V2 or Gemini 3.1 Pro?

Gemini 3.1 Pro scores higher overall with 87 vs 64, a difference of 23 points across all benchmarks.

Which is better for knowledge tasks, DeepSeekMath V2 or Gemini 3.1 Pro?

Gemini 3.1 Pro leads in knowledge tasks with an average score of 96 vs 77.8.

Which is better for coding, DeepSeekMath V2 or Gemini 3.1 Pro?

Gemini 3.1 Pro leads in coding with an average score of 91 vs 72.

Which is better for math, DeepSeekMath V2 or Gemini 3.1 Pro?

Gemini 3.1 Pro leads in math with an average score of 97.1 vs 79.

Which is better for reasoning, DeepSeekMath V2 or Gemini 3.1 Pro?

Gemini 3.1 Pro leads in reasoning with an average score of 94 vs 76.

Related Comparisons

DeepSeekMath V2 vs GPT-5.4DeepSeekMath V2 vs Claude Opus 4.6DeepSeekMath V2 vs GPT-5.3 CodexDeepSeekMath V2 vs Grok 4.1DeepSeekMath V2 vs GPT-5.2DeepSeekMath V2 vs GPT-5.2-Codex