Model comparison

DeepSeek-V3.1 vs Gemma 3n E4b IT

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 5.7× less per token, which makes it the better buy when DeepSeek-V3.1's lead doesn't matter for your workload.

Last verified October 10, 2026. 18 shared benchmarks.

DeepSeek-V3.1

DeepSeek

42.2

Rank #106 Confirmed

Gemma 3n E4b IT

Google

36.7

Rank #203 Confirmed

Summary

They share 18 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Gemma 3n E4b IT in 1 category; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.5 to 50.3.
The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for DeepSeek-V3.1 and 31.5% for Gemma 3n E4b IT.
Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
DeepSeek-V3.1 accepts more context: 164K tokens versus 33K.

Side by side

DeepSeek-V3.1 and Gemma 3n E4b IT specifications
	DeepSeek-V3.1	Gemma 3n E4b IT
Provider	DeepSeek	Google
Noometry Index	42.2	36.7
Released	2025-08-21	2025-05-20
Weights	Open	Open
Context window	164K	33K
Max output	8K	33K
Input $ / M tokens	$0.25	$0.06
Output $ / M tokens	$0.95	$0.12
Results tracked	27	18

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

Category by category

Coding DeepSeek-V3.1 leads

DeepSeek-V3.1: 39.8 (#140), Gemma 3n E4b IT: 36.4 (#193)

Coding benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Coding	1417	1269
WeirdML	38.4%	—

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), Gemma 3n E4b IT: 19.2 (#239)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
Kagi LLM Benchmark	53.2%	31.5%
LMArena Hard Prompts	1417	1284
SimpleBench	40%	—
DTBench	82.7%	—
LMCA	24.3%	—
Epoch Capabilities Index	139.92	—
ForecastBench	58	—

Math DeepSeek-V3.1 leads

DeepSeek-V3.1: 36.1 (#125), Gemma 3n E4b IT: 32.5 (#186)

Math benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Math	1420	1251

Knowledge DeepSeek-V3.1 leads

DeepSeek-V3.1: 43.0 (#86), Gemma 3n E4b IT: 33.6 (#193)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Expert	1403	1245
Vectara Hallucination Rate	5.5%	—

Multilingual DeepSeek-V3.1 leads

DeepSeek-V3.1: 51.8 (#100), Gemma 3n E4b IT: 43.5 (#179)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Non-English	1400	1285
LMArena Chinese	1470	1310
LMArena French	1447	1330
LMArena German	1412	1312
LMArena Japanese	1374	1274
LMArena Korean	1337	1259
LMArena Russian	1405	1288
LMArena Spanish	1429	1305

Instruction Following DeepSeek-V3.1 leads

DeepSeek-V3.1: 74.1 (#105), Gemma 3n E4b IT: 66.3 (#205)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Instruction Following	1400	1255

Long Context Gemma 3n E4b IT leads

DeepSeek-V3.1: 36.3 (#227), Gemma 3n E4b IT: 38.8 (#185)

Long Context benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Longer Query	1422	1277
Fiction.LiveBench	52.8%	—

Writing & Preference DeepSeek-V3.1 leads

DeepSeek-V3.1: 60.5 (#93), Gemma 3n E4b IT: 50.3 (#181)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1	Gemma 3n E4b IT
LMArena Text	1420	1306
LMArena Creative Writing	1401	1287
LMArena Multi-Turn	1408	1276
EQ-Bench Creative Writing	1436	—

Frequently asked questions

Is DeepSeek-V3.1 better than Gemma 3n E4b IT?

Which is cheaper, DeepSeek-V3.1 or Gemma 3n E4b IT?

Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; DeepSeek-V3.1 lists at $0.25 and $0.95.

Is DeepSeek-V3.1 or Gemma 3n E4b IT better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 36.4 in the Noometry coding category.

Which has the bigger context window?

DeepSeek-V3.1 does, with 164K tokens against 33K.

How many benchmarks do DeepSeek-V3.1 and Gemma 3n E4b IT share?

18 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Gemma 3n E4b IT has 18.