Noometry

Model comparison

MiniMax-M2 vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.5 to 36.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

MiniMax-M2 MiniMax

36.9

Rank #201 Confirmed

MiniMax-M3 MiniMax

43.5

Rank #81 Confirmed

Summary

  • They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 1 category and MiniMax-M3 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 36.3.
  • The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 65.1% for MiniMax-M3.
  • Both cost about the same: $0.30 input and $1.20 output per million tokens.
  • MiniMax-M3 accepts more context: 1M tokens versus 205K.

Side by side

MiniMax-M2MiniMax-M3
ProviderMiniMaxMiniMax
Noometry Index36.943.5
Released2025-10-272026-06-01
WeightsOpenOpen
Context window205K1M
Max output131K512K
Input $ / M tokens$0.30$0.30
Output $ / M tokens$1.20$1.20
Results tracked2141

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

Category by category

Coding MiniMax-M3 leads

MiniMax-M2: 39.1 (#151), MiniMax-M3: 41.5 (#111)

BenchmarkMiniMax-M2MiniMax-M3
LMArena WebDev12971482
LMArena Coding13701470
FrontierCode—14.7%
SWE-bench Verified (bash only)61%—
SciCode—47.1%
ALE-Bench—640.02

Agentic & Tool Use MiniMax-M2 leads

MiniMax-M2: 24.9 (#102), MiniMax-M3: 22.5 (#121)

BenchmarkMiniMax-M2MiniMax-M3
Vending-Bench 2160.62,158
Terminal-Bench30%—
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%

Reasoning MiniMax-M3 leads

MiniMax-M2: 18.6 (#256), MiniMax-M3: 29.3 (#83)

BenchmarkMiniMax-M2MiniMax-M3
NYT Connections (extended)14.8%65.1%
LMArena Hard Prompts13571447
SimpleBench—45.8%
Kagi LLM Benchmark57.8%—
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

MiniMax-M2: 34.6 (#158), MiniMax-M3: 39.1 (#83)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Math13501432
OTIS Mock AIME 2024-2025—71.1%
ProofBench—18%

Knowledge MiniMax-M3 leads

MiniMax-M2: 36.3 (#160), MiniMax-M3: 58.4 (#32)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Expert13361462
GPQA Diamond—90.9%

Multimodal Not comparable

MiniMax-M2: —, MiniMax-M3: 39.5 (#45)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Vision—1254
LMArena Document—1435

Multilingual MiniMax-M3 leads

MiniMax-M2: 45.6 (#165), MiniMax-M3: 53.2 (#70)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Non-English13141420
LMArena Chinese13671465
LMArena French13361445
LMArena German13661424
LMArena Russian13321430
LMArena Spanish13261431
LMArena Japanese—1381
LMArena Korean—1372

Instruction Following MiniMax-M3 leads

MiniMax-M2: 70.4 (#160), MiniMax-M3: 75.7 (#56)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Instruction Following13291433

Long Context MiniMax-M3 leads

MiniMax-M2: 40.5 (#148), MiniMax-M3: 44.2 (#68)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Longer Query13321445

Writing & Preference MiniMax-M3 leads

MiniMax-M2: 53.3 (#157), MiniMax-M3: 62.3 (#79)

BenchmarkMiniMax-M2MiniMax-M3
LMArena Text13401433
LMArena Creative Writing12881405
LMArena Multi-Turn13621441
EQ-Bench 4—1150

Frequently asked questions

Is MiniMax-M2 better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 36.9 on the Noometry Index.

Which is cheaper, MiniMax-M2 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

Is MiniMax-M2 or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 205K.

How many benchmarks do MiniMax-M2 and MiniMax-M3 share?

18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper