Noometry

Model comparison

Gemma 2 9B vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 to 25.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Gemma 2 9B Google

25.9

Rank #341 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 9.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 71.1% for MiniMax-M3.

Side by side

Gemma 2 9BMiniMax-M3
ProviderGoogleMiniMax
Noometry Index25.943.8
Released2024-06-242026-06-01
WeightsOpenOpen
Context window—1M
Max output—512K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3541

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

Category by category

Coding MiniMax-M3 leads

Gemma 2 9B: 29.4 (#304), MiniMax-M3: 41.8 (#118)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Coding11731469
FrontierCode—14.7%
LMArena WebDev—1482
SciCode—47.1%
BigCodeBench Instruct34.7%—
LiveBench Coding22.5%—
BigCodeBench Complete40.6%—
ALE-Bench—640.02

Agentic & Tool Use Not comparable

Gemma 2 9B: —, MiniMax-M3: 22.6 (#130)

BenchmarkGemma 2 9BMiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning MiniMax-M3 leads

Gemma 2 9B: 15.9 (#309), MiniMax-M3: 30.1 (#87)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Hard Prompts11711447
Epoch Capabilities Index119.83146.95
SimpleBench—45.8%
NYT Connections (extended)—65.1%
CritPt—3.7%
Chess Puzzles—14%
LiveBench Reasoning15.2%—
Mystery Game Puzzles—8%
DTBench—78.9%
LiveBench Data Analysis36.4%—
LMCA—33.7%
Surface Evolver Bench—55%
ForecastBench—61.4
LiveBench28.7%—
PIQA83.7%—

Math MiniMax-M3 leads

Gemma 2 9B: 9.9 (#318), MiniMax-M3: 40.0 (#95)

BenchmarkGemma 2 9BMiniMax-M3
OTIS Mock AIME 2024-20250.6%71.1%
LMArena Math11831429
ProofBench—18%
LiveBench Math19.8%—
MATH Level 521%—
GSM8K84.9%—

Knowledge MiniMax-M3 leads

Gemma 2 9B: 9.7 (#305), MiniMax-M3: 58.4 (#35)

BenchmarkGemma 2 9BMiniMax-M3
GPQA Diamond27.5%90.9%
LMArena Expert11471461
BoolQ85.7%—
MMLU72.1%—

Multimodal Not comparable

Gemma 2 9B: —, MiniMax-M3: 40.2 (#51)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Vision—1253
LMArena Document—1435

Multilingual MiniMax-M3 leads

Gemma 2 9B: 36.6 (#238), MiniMax-M3: 53.0 (#75)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Non-English11881420
LMArena Chinese11851463
LMArena French11901447
LMArena German11861426
LMArena Japanese11441381
LMArena Korean11371372
LMArena Russian12001428
LMArena Spanish12001432

Instruction Following MiniMax-M3 leads

Gemma 2 9B: 57.6 (#269), MiniMax-M3: 75.5 (#62)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Instruction Following11781433
LiveBench Instruction Following52.6%—

Long Context MiniMax-M3 leads

Gemma 2 9B: 36.3 (#233), MiniMax-M3: 44.2 (#72)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Longer Query11971445

Writing & Preference MiniMax-M3 leads

Gemma 2 9B: 32.1 (#281), MiniMax-M3: 62.1 (#83)

BenchmarkGemma 2 9BMiniMax-M3
LMArena Text12071433
LMArena Creative Writing12061404
LMArena Multi-Turn11931442
EQ-Bench Creative Writing841—
EQ-Bench 4—1150
LiveBench Language25.5%—

Frequently asked questions

Is Gemma 2 9B better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 25.9 on the Noometry Index.

Is Gemma 2 9B or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2 9B and MiniMax-M3 share?

20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper