Model comparison

Gemma 3n E4b IT vs Mercury 2

Mercury 2 is the stronger model overall, scoring 38.8 to 36.7 on the Noometry Index. Gemma 3n E4b IT costs 5.0× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

Last verified October 10, 2026. 11 shared benchmarks.

Gemma 3n E4b IT

Google

36.7

Rank #203 Confirmed

Mercury 2 Inception

38.8

Rank #167 Confirmed

Summary

They share 11 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 1 category and Mercury 2 in 6 categories; 7 gaps are clear of the uncertainty.
The widest gap is in instruction following, where Mercury 2 leads 70.4 to 66.3.
Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
Mercury 2 accepts more context: 128K tokens versus 33K.
Gemma 3n E4b IT has downloadable open weights; the other is API-only.

Side by side

Gemma 3n E4b IT and Mercury 2 specifications
	Gemma 3n E4b IT	Mercury 2
Provider	Google	Inception
Noometry Index	36.7	38.8
Released	2025-05-20	2026-02-20
Weights	Open	Proprietary
Context window	33K	128K
Max output	33K	50K
Input $ / M tokens	$0.06	$0.25
Output $ / M tokens	$0.12	$0.75
Results tracked	18	17

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

Category by category

Coding Gemma 3n E4b IT leads

Gemma 3n E4b IT: 36.4 (#193), Mercury 2: 33.2 (#250)

Coding benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Coding	1269	1391
LMArena WebDev	—	1170
SciCode	—	38.7%
WeirdML	—	43.2%
ALE-Bench	—	785.58

Reasoning Mercury 2 leads

Gemma 3n E4b IT: 19.2 (#239), Mercury 2: 23.0 (#170)

Reasoning benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Hard Prompts	1284	1362
Kagi LLM Benchmark	31.5%	—
CritPt	—	0.8%

Math Not comparable

Gemma 3n E4b IT: 32.5 (#186), Mercury 2: —

Math benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Math	1251	—

Knowledge Mercury 2 leads

Gemma 3n E4b IT: 33.6 (#193), Mercury 2: 35.6 (#170)

Knowledge benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Expert	1245	1358
Vectara Hallucination Rate	—	12.3%

Multilingual Mercury 2 leads

Gemma 3n E4b IT: 43.5 (#179), Mercury 2: 46.8 (#153)

Multilingual benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Non-English	1285	1331
LMArena Chinese	1310	1416
LMArena Russian	1288	1303
LMArena French	1330	—
LMArena German	1312	—
LMArena Japanese	1274	—
LMArena Korean	1259	—
LMArena Spanish	1305	—

Instruction Following Mercury 2 leads

Gemma 3n E4b IT: 66.3 (#205), Mercury 2: 70.4 (#161)

Instruction Following benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Instruction Following	1255	1328

Long Context Mercury 2 leads

Gemma 3n E4b IT: 38.8 (#185), Mercury 2: 40.4 (#149)

Long Context benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Longer Query	1277	1329

Writing & Preference Mercury 2 leads

Gemma 3n E4b IT: 50.3 (#181), Mercury 2: 54.0 (#151)

Writing & Preference benchmarks
Benchmark	Gemma 3n E4b IT	Mercury 2
LMArena Text	1306	1355
LMArena Creative Writing	1287	1289
LMArena Multi-Turn	1276	1358

Frequently asked questions

Is Gemma 3n E4b IT better than Mercury 2?

Which is cheaper, Gemma 3n E4b IT or Mercury 2?

Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

Is Gemma 3n E4b IT or Mercury 2 better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Mercury 2 does, with 128K tokens against 33K.

How many benchmarks do Gemma 3n E4b IT and Mercury 2 share?

11 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Mercury 2 has 17.