benchlm.ai

DeepSeek V3.2 vs Gemini 2.5 Pro

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

Quick Verdict

DeepSeek V3.2 wins overall with a score of 66 vs 65 (1 point difference).DeepSeek V3.2 wins 2 out of 4 categories.

DeepSeek V3.2

CreatorDeepSeek
TypeOpen Weight
Context128K
Score66

Gemini 2.5 Pro

CreatorGoogle
TypeProprietary
Context2M
Score65

Knowledge

DeepSeek V3.2

DeepSeek V3.2

81.8

Gemini 2.5 Pro

81.5

84
MMLU
83
83
GPQA
83
81
SuperGPQA
81
79
OpenBookQA
79

Coding

DeepSeek V3.2

DeepSeek V3.2

76

Gemini 2.5 Pro

75

76
HumanEval
75

Mathematics

Tie

DeepSeek V3.2

83

Gemini 2.5 Pro

83

84
AIME 2023
84
86
AIME 2024
86
85
AIME 2025
85
80
HMMT Feb 2023
80
82
HMMT Feb 2024
82
81
HMMT Feb 2025
81
83
BRUMO 2025
83

Reasoning

Tie

DeepSeek V3.2

80

Gemini 2.5 Pro

80

81
SimpleQA
81
79
MuSR
79

Frequently Asked Questions

Which is better, DeepSeek V3.2 or Gemini 2.5 Pro?

DeepSeek V3.2 scores higher overall with 66 vs 65, a difference of 1 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek V3.2 or Gemini 2.5 Pro?

DeepSeek V3.2 leads in knowledge tasks with an average score of 81.8 vs 81.5.

Which is better for coding, DeepSeek V3.2 or Gemini 2.5 Pro?

DeepSeek V3.2 leads in coding with an average score of 76 vs 75.

Which is better for math, DeepSeek V3.2 or Gemini 2.5 Pro?

DeepSeek V3.2 and Gemini 2.5 Pro are tied for math with average scores of 83.

Which is better for reasoning, DeepSeek V3.2 or Gemini 2.5 Pro?

DeepSeek V3.2 and Gemini 2.5 Pro are tied for reasoning with average scores of 80.

Related Comparisons

DeepSeek V3.2 vs GPT-5.4DeepSeek V3.2 vs Gemini 3.1 ProDeepSeek V3.2 vs Claude Opus 4.6DeepSeek V3.2 vs GPT-5.3 CodexDeepSeek V3.2 vs Grok 4.1DeepSeek V3.2 vs GPT-5.2