Model comparison

DeepSeek-V3.2-Speciale vs Gemma 4 31B IT

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 39.1 on the Noometry Index.

Last verified October 10, 2026. 2 shared benchmarks.

DeepSeek-V3.2-Speciale

DeepSeek

39.1

Rank #159 Reported

Gemma 4 31B IT

Google

43.2

Rank #85 Confirmed

Summary

They share 2 benchmarks with published results for both. DeepSeek-V3.2-Speciale scores higher in 1 category and Gemma 4 31B IT in 2 categories; 3 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.7 to 46.1.
The biggest single-benchmark swing is WeirdML: 46.7% for DeepSeek-V3.2-Speciale and 52.3% for Gemma 4 31B IT.
Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.58 / $1.68 for DeepSeek-V3.2-Speciale.
Gemma 4 31B IT accepts more context: 262K tokens versus 128K.

Side by side

DeepSeek-V3.2-Speciale and Gemma 4 31B IT specifications
	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
Provider	DeepSeek	Google
Noometry Index	39.1	43.2
Released	2025-12-01	2026-04-02
Weights	Open	Open
Context window	128K	262K
Max output	128K	33K
Input $ / M tokens	$0.58	$0.09
Output $ / M tokens	$1.68	$0.34
Results tracked	3	35

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemma 4 31B IT leads

DeepSeek-V3.2-Speciale: 39.9 (#136), Gemma 4 31B IT: 41.9 (#98)

Coding benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
WeirdML	46.7%	52.3%
LMArena WebDev	—	1364
SciCode	—	43.4%
LMArena Coding	—	1459
ALE-Bench	—	925.5

Reasoning DeepSeek-V3.2-Speciale leads

DeepSeek-V3.2-Speciale: 32.1 (#65), Gemma 4 31B IT: 26.4 (#119)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
SimpleBench	52.6%	—
Kagi LLM Benchmark	—	63.5%
NYT Connections (extended)	—	70.6%
CritPt	—	1.4%
Chess Puzzles	—	5%
Thematic Generalization	—	53%
LMArena Hard Prompts	—	1448
DTBench	—	82.7%
LMCA	—	39.3%
Surface Evolver Bench	—	30.6%
Epoch Capabilities Index	—	142.74

Math Not comparable

DeepSeek-V3.2-Speciale: —, Gemma 4 31B IT: 41.3 (#72)

Math benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
OTIS Mock AIME 2024-2025	—	73.3%
LMArena Math	—	1464

Knowledge Not comparable

DeepSeek-V3.2-Speciale: —, Gemma 4 31B IT: 37.9 (#141)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
GPQA Diamond	—	75.8%
SimpleQA Verified	—	10.4%
Vectara Hallucination Rate	—	7.4%
LMArena Expert	—	1465

Multimodal Not comparable

DeepSeek-V3.2-Speciale: —, Gemma 4 31B IT: 41.0 (#32)

Multimodal benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
LMArena Vision	—	1278
LMArena Document	—	1425

Multilingual Not comparable

DeepSeek-V3.2-Speciale: —, Gemma 4 31B IT: 54.0 (#52)

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
LMArena Non-English	—	1431
LMArena Chinese	—	1478
LMArena French	—	1436
LMArena Russian	—	1462
LMArena Spanish	—	1443

Instruction Following Not comparable

DeepSeek-V3.2-Speciale: —, Gemma 4 31B IT: 75.6 (#58)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
LMArena Instruction Following	—	1433

Long Context Not comparable

DeepSeek-V3.2-Speciale: —, Gemma 4 31B IT: 44.2 (#67)

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
LMArena Longer Query	—	1446

Writing & Preference Gemma 4 31B IT leads

DeepSeek-V3.2-Speciale: 46.1 (#217), Gemma 4 31B IT: 60.7 (#92)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Speciale	Gemma 4 31B IT
EQ-Bench Creative Writing	1276	1368
LMArena Text	—	1443
LMArena Creative Writing	—	1416
EQ-Bench 4	—	1120
LMArena Multi-Turn	—	1452

Frequently asked questions

Is DeepSeek-V3.2-Speciale better than Gemma 4 31B IT?

Gemma 4 31B IT is the stronger model overall, scoring 43.2 to 39.1 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Speciale or Gemma 4 31B IT?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; DeepSeek-V3.2-Speciale lists at $0.58 and $1.68.

Is DeepSeek-V3.2-Speciale or Gemma 4 31B IT better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 41.9 versus 39.9 in the Noometry coding category.

Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 128K.

How many benchmarks do DeepSeek-V3.2-Speciale and Gemma 4 31B IT share?

2 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Gemma 4 31B IT has 35.