Model comparison

Devstral Small 2505 vs Gemma 3n E4b IT

Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 33.9 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

Devstral Small 2505

Mistral AI

33.9

Rank #228 Reported

Gemma 3n E4b IT

Google

36.7

Rank #203 Confirmed

Summary

They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 1 category and Gemma 3n E4b IT in 1 category; one gap is clear of the uncertainty.
The biggest single-benchmark swing is Kagi LLM Benchmark: 37.7% for Devstral Small 2505 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 $0.10 / $0.30 for Devstral Small 2505.
Devstral Small 2505 accepts more context: 128K tokens versus 33K.

Side by side

Devstral Small 2505 and Gemma 3n E4b IT specifications
	Devstral Small 2505	Gemma 3n E4b IT
Provider	Mistral AI	Google
Noometry Index	33.9	36.7
Released	2025-05-07	2025-05-20
Weights	Open	Open
Context window	128K	33K
Max output	128K	33K
Input $ / M tokens	$0.10	$0.06
Output $ / M tokens	$0.30	$0.12
Results tracked	4	18

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

Category by category

Coding Devstral Small 2505 leads

Devstral Small 2505: 38.6 (#160), Gemma 3n E4b IT: 36.4 (#193)

Coding benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
SWE-bench Verified (bash only)	56.4%	—
SciCode	28.8%	—
LMArena Coding	—	1269

Reasoning Too close to call

Devstral Small 2505: 19.1 (#243), Gemma 3n E4b IT: 19.2 (#239)

Reasoning benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
Kagi LLM Benchmark	37.7%	31.5%
CritPt	0%	—
LMArena Hard Prompts	—	1284

Math Not comparable

Devstral Small 2505: —, Gemma 3n E4b IT: 32.5 (#186)

Math benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
LMArena Math	—	1251

Knowledge Not comparable

Devstral Small 2505: —, Gemma 3n E4b IT: 33.6 (#193)

Knowledge benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
LMArena Expert	—	1245

Multilingual Not comparable

Devstral Small 2505: —, Gemma 3n E4b IT: 43.5 (#179)

Multilingual benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
LMArena Non-English	—	1285
LMArena Chinese	—	1310
LMArena French	—	1330
LMArena German	—	1312
LMArena Japanese	—	1274
LMArena Korean	—	1259
LMArena Russian	—	1288
LMArena Spanish	—	1305

Instruction Following Not comparable

Devstral Small 2505: —, Gemma 3n E4b IT: 66.3 (#205)

Instruction Following benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
LMArena Instruction Following	—	1255

Long Context Not comparable

Devstral Small 2505: —, Gemma 3n E4b IT: 38.8 (#185)

Long Context benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
LMArena Longer Query	—	1277

Writing & Preference Not comparable

Devstral Small 2505: —, Gemma 3n E4b IT: 50.3 (#181)

Writing & Preference benchmarks
Benchmark	Devstral Small 2505	Gemma 3n E4b IT
LMArena Text	—	1306
LMArena Creative Writing	—	1287
LMArena Multi-Turn	—	1276

Frequently asked questions

Is Devstral Small 2505 better than Gemma 3n E4b IT?

Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 33.9 on the Noometry Index.

Which is cheaper, Devstral Small 2505 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; Devstral Small 2505 lists at $0.10 and $0.30.

Is Devstral Small 2505 or Gemma 3n E4b IT better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 36.4 in the Noometry coding category.

Which has the bigger context window?

Devstral Small 2505 does, with 128K tokens against 33K.

How many benchmarks do Devstral Small 2505 and Gemma 3n E4b IT share?

1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Gemma 3n E4b IT has 18.