Model comparison

Gemma 2B vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 to 29.6 on the Noometry Index.

Last verified October 10, 2026. 12 shared benchmarks.

Gemma 2B

Google

29.6

Rank #307 Confirmed

MiniMax-M3

MiniMax

43.8

Rank #85 Confirmed

Summary

They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and MiniMax-M3 in 7 categories; 7 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 to 24.0.

Side by side

Gemma 2B and MiniMax-M3 specifications
	Gemma 2B	MiniMax-M3
Provider	Google	MiniMax
Noometry Index	29.6	43.8
Released	2024-02-21	2026-06-01
Weights	Open	Open
Context window	—	1M
Max output	—	512K
Input $ / M tokens	—	$0.30
Output $ / M tokens	—	$1.20
Results tracked	23	41

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

Category by category

Coding MiniMax-M3 leads

Gemma 2B: 29.4 (#305), MiniMax-M3: 41.8 (#118)

Coding benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Coding	1010	1469
FrontierCode	—	14.7%
LMArena WebDev	—	1482
SciCode	—	47.1%
ALE-Bench	—	640.02
HumanEval+	20.7%	—
MBPP+	34.1%	—

Agentic & Tool Use Not comparable

Gemma 2B: —, MiniMax-M3: 22.6 (#130)

Agentic & Tool Use benchmarks
Benchmark	Gemma 2B	MiniMax-M3
APEX-Agents	—	37.7%
OSWorld 2.0	—	4.6%
GBAEval	—	0.9%
Vending-Bench 2	—	2,158

Reasoning MiniMax-M3 leads

Gemma 2B: 18.8 (#275), MiniMax-M3: 30.1 (#87)

Reasoning benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Hard Prompts	989	1447
Epoch Capabilities Index	94.2	146.95
SimpleBench	—	45.8%
NYT Connections (extended)	—	65.1%
CritPt	—	3.7%
Chess Puzzles	—	14%
Mystery Game Puzzles	—	8%
DTBench	—	78.9%
LMCA	—	33.7%
Surface Evolver Bench	—	55%
BIG-Bench Hard	35.2%	—
ForecastBench	—	61.4
HellaSwag	71.4%	—
PIQA	77.3%	—
WinoGrande	65.4%	—

Math MiniMax-M3 leads

Gemma 2B: 30.0 (#239), MiniMax-M3: 40.0 (#95)

Math benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Math	1009	1429
OTIS Mock AIME 2024-2025	—	71.1%
ProofBench	—	18%
GSM8K	17.7%	—

Knowledge Not comparable

Gemma 2B: —, MiniMax-M3: 58.4 (#35)

Knowledge benchmarks
Benchmark	Gemma 2B	MiniMax-M3
GPQA Diamond	—	90.9%
LMArena Expert	—	1461
ARC (AI2) Challenge	42.1%	—
BoolQ	69.4%	—
MMLU	42.3%	—
TriviaQA	53.2%	—

Multimodal Not comparable

Gemma 2B: —, MiniMax-M3: 40.2 (#51)

Multimodal benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Vision	—	1253
LMArena Document	—	1435

Multilingual MiniMax-M3 leads

Gemma 2B: 23.0 (#294), MiniMax-M3: 53.0 (#75)

Multilingual benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Non-English	958	1420
LMArena Chinese	986	1463
LMArena Russian	937	1428
LMArena French	—	1447
LMArena German	—	1426
LMArena Japanese	—	1381
LMArena Korean	—	1372
LMArena Spanish	—	1432

Instruction Following MiniMax-M3 leads

Gemma 2B: 48.5 (#302), MiniMax-M3: 75.5 (#62)

Instruction Following benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Instruction Following	970	1433

Long Context MiniMax-M3 leads

Gemma 2B: 29.9 (#291), MiniMax-M3: 44.2 (#72)

Long Context benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Longer Query	981	1445

Writing & Preference MiniMax-M3 leads

Gemma 2B: 24.0 (#308), MiniMax-M3: 62.1 (#83)

Writing & Preference benchmarks
Benchmark	Gemma 2B	MiniMax-M3
LMArena Text	1002	1433
LMArena Creative Writing	987	1404
LMArena Multi-Turn	945	1442
EQ-Bench 4	—	1150

Frequently asked questions

Is Gemma 2B better than MiniMax-M3?