Noometry

Model comparison

Granite 3.0 2b Instruct vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.5 to 30.2 on the Noometry Index.

Last verified . 12 shared benchmarks.

Granite 3.0 2b Instruct IBM

30.2

Rank #284 Confirmed

MiniMax-M3 MiniMax

43.5

Rank #81 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 0 categories and MiniMax-M3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiniMax-M3 leads 62.3 to 29.8.

Side by side

Granite 3.0 2b InstructMiniMax-M3
ProviderIBMMiniMax
Noometry Index30.243.5
Released—2026-06-01
WeightsOpenOpen
Context window—1M
Max output—512K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked1341

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

Category by category

Coding MiniMax-M3 leads

Granite 3.0 2b Instruct: 27.8 (#311), MiniMax-M3: 41.5 (#111)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Coding10901470
FrontierCode—14.7%
LMArena WebDev—1482
SciCode—47.1%
BigCodeBench Instruct20.5%—
ALE-Bench—640.02

Agentic & Tool Use Not comparable

Granite 3.0 2b Instruct: —, MiniMax-M3: 22.5 (#121)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning MiniMax-M3 leads

Granite 3.0 2b Instruct: 19.6 (#234), MiniMax-M3: 29.3 (#83)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Hard Prompts10731447
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%
Epoch Capabilities Index—147
ForecastBench—61.4

Math MiniMax-M3 leads

Granite 3.0 2b Instruct: 29.7 (#215), MiniMax-M3: 39.1 (#83)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Math11171432
OTIS Mock AIME 2024-2025—71.1%
ProofBench—18%

Knowledge MiniMax-M3 leads

Granite 3.0 2b Instruct: 28.4 (#238), MiniMax-M3: 58.4 (#32)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Expert10641462
GPQA Diamond—90.9%

Multimodal Not comparable

Granite 3.0 2b Instruct: —, MiniMax-M3: 39.5 (#45)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Vision—1254
LMArena Document—1435

Multilingual MiniMax-M3 leads

Granite 3.0 2b Instruct: 27.1 (#273), MiniMax-M3: 53.2 (#70)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Non-English10331420
LMArena Chinese10701465
LMArena Russian10451430
LMArena French—1445
LMArena German—1424
LMArena Japanese—1381
LMArena Korean—1372
LMArena Spanish—1431

Instruction Following MiniMax-M3 leads

Granite 3.0 2b Instruct: 54.2 (#279), MiniMax-M3: 75.7 (#56)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Instruction Following10561433

Long Context MiniMax-M3 leads

Granite 3.0 2b Instruct: 32.5 (#263), MiniMax-M3: 44.2 (#68)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Longer Query10711445

Writing & Preference MiniMax-M3 leads

Granite 3.0 2b Instruct: 29.8 (#287), MiniMax-M3: 62.3 (#79)

BenchmarkGranite 3.0 2b InstructMiniMax-M3
LMArena Text10801433
LMArena Creative Writing10461405
LMArena Multi-Turn10531441
EQ-Bench 4—1150

Frequently asked questions

Is Granite 3.0 2b Instruct better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 30.2 on the Noometry Index.

Is Granite 3.0 2b Instruct or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 27.8 in the Noometry coding category.

How many benchmarks do Granite 3.0 2b Instruct and MiniMax-M3 share?

12 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper