Noometry

Model comparison

Gemma 3 4B vs MiniMax-M2

MiniMax-M2 is the stronger model overall, scoring 37.4 to 28.1 on the Noometry Index. Gemma 3 4B costs 10× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

Last verified . 13 shared benchmarks.

Gemma 3 4B Google

28.1

Rank #326 Confirmed

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and MiniMax-M2 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M2 leads 37.0 to 11.8.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 57.8% for MiniMax-M2.
  • Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
  • MiniMax-M2 accepts more context: 205K tokens versus 131K.

Side by side

Gemma 3 4BMiniMax-M2
ProviderGoogleMiniMax
Noometry Index28.137.4
Released2025-03-122025-10-27
WeightsOpenOpen
Context window131K205K
Max output4K131K
Input $ / M tokens$0.04$0.30
Output $ / M tokens$0.08$1.20
Results tracked2221

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

Category by category

Coding MiniMax-M2 leads

Gemma 3 4B: 35.9 (#215), MiniMax-M2: 39.3 (#159)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Coding12301370
SWE-bench Verified (bash only)—61%
LMArena WebDev—1297

Agentic & Tool Use MiniMax-M2 leads

Gemma 3 4B: 20.9 (#142), MiniMax-M2: 25.1 (#109)

BenchmarkGemma 3 4BMiniMax-M2
Terminal-Bench—30%
Berkeley Function Calling Leaderboard19.6%—
Vending-Bench 2—160.6

Reasoning MiniMax-M2 leads

Gemma 3 4B: 13.2 (#335), MiniMax-M2: 19.4 (#258)

BenchmarkGemma 3 4BMiniMax-M2
Kagi LLM Benchmark25.2%57.8%
LMArena Hard Prompts12531357
NYT Connections (extended)—14.8%
Chess Puzzles0%—
DTBench50.9%—
LMCA2.8%—
Epoch Capabilities Index116.02—

Math MiniMax-M2 leads

Gemma 3 4B: 16.8 (#292), MiniMax-M2: 37.3 (#160)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Math12391352
OTIS Mock AIME 2024-20257.5%—

Knowledge MiniMax-M2 leads

Gemma 3 4B: 11.8 (#299), MiniMax-M2: 37.0 (#163)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Expert12231337
GPQA Diamond23.2%—
Vectara Hallucination Rate6.4%—

Multilingual MiniMax-M2 leads

Gemma 3 4B: 42.5 (#194), MiniMax-M2: 45.3 (#171)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Non-English12731313
LMArena German12811355
LMArena Russian12941331
LMArena Chinese—1366
LMArena French—1335
LMArena Spanish—1326

Instruction Following MiniMax-M2 leads

Gemma 3 4B: 65.2 (#225), MiniMax-M2: 70.2 (#166)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Instruction Following12391328

Long Context MiniMax-M2 leads

Gemma 3 4B: 38.7 (#194), MiniMax-M2: 40.5 (#153)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Longer Query12731331

Writing & Preference MiniMax-M2 leads

Gemma 3 4B: 42.0 (#239), MiniMax-M2: 53.0 (#162)

BenchmarkGemma 3 4BMiniMax-M2
LMArena Text12911340
LMArena Creative Writing12711286
LMArena Multi-Turn12551361
EQ-Bench Creative Writing1068—

Frequently asked questions

Is Gemma 3 4B better than MiniMax-M2?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 28.1 on the Noometry Index. Gemma 3 4B costs 10× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

Which is cheaper, Gemma 3 4B or MiniMax-M2?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

Is Gemma 3 4B or MiniMax-M2 better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2 does, with 205K tokens against 131K.

How many benchmarks do Gemma 3 4B and MiniMax-M2 share?

13 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and MiniMax-M2 has 21.

Related comparisons

Go deeper