benchlm.ai

DeepSeek V3.1 (Reasoning) vs Nova Pro

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

Quick Verdict

Nova Pro wins overall with a score of 32 vs 25 (7 point difference).Nova Pro wins 4 out of 4 categories.

DeepSeek V3.1 (Reasoning)

CreatorDeepSeek
TypeOpen Weight
Context128K
Score25

Nova Pro

CreatorNova AI
TypeProprietary
Context128K
Score32

Knowledge

Nova Pro

DeepSeek V3.1 (Reasoning)

31.8

Nova Pro

38.8

34
MMLU
41
33
GPQA
40
31
SuperGPQA
38
29
OpenBookQA
36

Coding

Nova Pro

DeepSeek V3.1 (Reasoning)

26

Nova Pro

33

26
HumanEval
33

Mathematics

Nova Pro

DeepSeek V3.1 (Reasoning)

33

Nova Pro

40

34
AIME 2023
41
36
AIME 2024
43
35
AIME 2025
42
30
HMMT Feb 2023
37
32
HMMT Feb 2024
39
31
HMMT Feb 2025
38
33
BRUMO 2025
40

Reasoning

Nova Pro

DeepSeek V3.1 (Reasoning)

31

Nova Pro

38

32
SimpleQA
39
30
MuSR
37

Frequently Asked Questions

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

Nova Pro scores higher overall with 32 vs 25, a difference of 7 points across all benchmarks.

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

Nova Pro leads in knowledge tasks with an average score of 38.8 vs 31.8.

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

Nova Pro leads in coding with an average score of 33 vs 26.

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

Nova Pro leads in math with an average score of 40 vs 33.

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

Nova Pro leads in reasoning with an average score of 38 vs 31.

Related Comparisons

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