Model comparison

DeepSeek-V3.1-Terminus vs Gemma 4 31B IT

DeepSeek-V3.1-Terminus and Gemma 4 31B IT score almost the same on the Noometry Index (43.1 vs 43.5), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 16 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

43.1

Rank #97 Confirmed

Gemma 4 31B IT

Google

43.5

Rank #90 Confirmed

Summary

They share 16 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 1 category and Gemma 4 31B IT in 6 categories; 3 gaps are clear of the uncertainty.
The widest gap is in math, where Gemma 4 31B IT leads 43.2 to 38.5.
The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 39.3% for Gemma 4 31B IT.
Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
Gemma 4 31B IT accepts more context: 262K tokens versus 164K.

Side by side

DeepSeek-V3.1-Terminus and Gemma 4 31B IT specifications
	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
Provider	DeepSeek	Google
Noometry Index	43.1	43.5
Released	2025-09-22	2026-04-02
Weights	Open	Open
Context window	164K	262K
Max output	147K	33K
Input $ / M tokens	$0.27	$0.09
Output $ / M tokens	$1	$0.34
Results tracked	16	35

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

Category by category

Coding Too close to call

DeepSeek-V3.1-Terminus: 42.0 (#113), Gemma 4 31B IT: 42.3 (#108)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
SciCode	40.6%	43.4%
LMArena Coding	1426	1459
ALE-Bench	745.17	925.5
LMArena WebDev	—	1366
WeirdML	—	52.3%

Reasoning Too close to call

DeepSeek-V3.1-Terminus: 26.4 (#133), Gemma 4 31B IT: 27.2 (#122)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
Kagi LLM Benchmark	57.4%	63.5%
CritPt	1.7%	1.4%
LMArena Hard Prompts	1426	1448
DTBench	81.3%	82.7%
LMCA	28.6%	39.3%
NYT Connections (extended)	—	70.6%
Chess Puzzles	—	5%
Thematic Generalization	—	53%
Surface Evolver Bench	—	30.6%
Epoch Capabilities Index	—	142.74

Math Gemma 4 31B IT leads

DeepSeek-V3.1-Terminus: 38.5 (#137), Gemma 4 31B IT: 43.2 (#81)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
LMArena Math	1402	1465
OTIS Mock AIME 2024-2025	—	73.3%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Gemma 4 31B IT: 37.9 (#151)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
GPQA Diamond	—	75.8%
SimpleQA Verified	—	10.4%
Vectara Hallucination Rate	—	7.4%
LMArena Expert	—	1465

Multimodal Not comparable

DeepSeek-V3.1-Terminus: —, Gemma 4 31B IT: 41.6 (#34)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
LMArena Vision	—	1277
LMArena Document	—	1425

Multilingual Gemma 4 31B IT leads

DeepSeek-V3.1-Terminus: 52.1 (#92), Gemma 4 31B IT: 53.8 (#57)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
LMArena Non-English	1407	1431
LMArena Russian	1436	1460
LMArena Chinese	—	1476
LMArena French	—	1435
LMArena Spanish	—	1444

Instruction Following Gemma 4 31B IT leads

DeepSeek-V3.1-Terminus: 74.0 (#106), Gemma 4 31B IT: 75.5 (#61)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
LMArena Instruction Following	1404	1433

Long Context Too close to call

DeepSeek-V3.1-Terminus: 43.4 (#97), Gemma 4 31B IT: 44.2 (#71)

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
LMArena Longer Query	1421	1446

Writing & Preference Too close to call

DeepSeek-V3.1-Terminus: 61.0 (#92), Gemma 4 31B IT: 60.5 (#96)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemma 4 31B IT
LMArena Text	1419	1443
LMArena Creative Writing	1403	1415
LMArena Multi-Turn	1411	1452
EQ-Bench Creative Writing	—	1368
EQ-Bench 4	—	1120

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Gemma 4 31B IT?

DeepSeek-V3.1-Terminus and Gemma 4 31B IT score almost the same on the Noometry Index (43.1 vs 43.5), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-V3.1-Terminus 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-V3.1-Terminus lists at $0.27 and $1.

Is DeepSeek-V3.1-Terminus or Gemma 4 31B IT better for coding?

They score almost the same on coding (42.0 vs 42.3); test both on your own repository before choosing.

Which has the bigger context window?

Gemma 4 31B IT does, with 262K tokens against 164K.

How many benchmarks do DeepSeek-V3.1-Terminus and Gemma 4 31B IT share?

16 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemma 4 31B IT has 35.