Noometry

Model comparison

MiniMax M1 vs MiniMax-M2.5

MiniMax M1 is the stronger model overall, scoring 39.7 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 1.6× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.

Last verified . 17 shared benchmarks.

MiniMax M1 MiniMax

39.7

Rank #146 Confirmed

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

Summary

  • They share 17 benchmarks with published results for both. MiniMax M1 scores higher in 3 categories and MiniMax-M2.5 in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax M1 leads 34.8 to 25.8.
  • MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $2.20 for MiniMax M1.
  • MiniMax M1 accepts more context: 1M tokens versus 205K.

Side by side

MiniMax M1MiniMax-M2.5
ProviderMiniMaxMiniMax
Noometry Index39.738.1
Released2025-06-132026-02-12
WeightsOpenOpen
Context window1M205K
Max output40K131K
Input $ / M tokens$0.40$0.30
Output $ / M tokens$2.20$1.20
Results tracked1833

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax M1: 39.2 (#149), MiniMax-M2.5: 47.9 (#53)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Coding13591380
SWE-bench Verified (bash only)—75.8%
LMArena WebDev—1386
SWE-bench Multilingual—68.3%
ALE-Bench—618.17

Agentic & Tool Use Not comparable

MiniMax M1: —, MiniMax-M2.5: 30.2 (#70)

BenchmarkMiniMax M1MiniMax-M2.5
Terminal-Bench—42.7%
Vending-Bench 2—-23.16

Reasoning MiniMax M1 leads

MiniMax M1: 25.8 (#125), MiniMax-M2.5: 17.6 (#281)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Hard Prompts13401372
ARC-AGI-2—4.9%
Kagi LLM Benchmark—55.2%
NYT Connections (extended)—16.8%
ARC-AGI-1—63.7%
Epoch Capabilities Index—146.68

Math MiniMax M1 leads

MiniMax M1: 34.8 (#152), MiniMax-M2.5: 25.8 (#242)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Math13601378
ProofBench—4%

Knowledge MiniMax-M2.5 leads

MiniMax M1: 35.7 (#168), MiniMax-M2.5: 38.6 (#132)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Expert13161378
Vectara Hallucination Rate—9.1%

Multilingual MiniMax-M2.5 leads

MiniMax M1: 46.0 (#157), MiniMax-M2.5: 47.3 (#147)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Non-English13201338
LMArena Chinese13611392
LMArena French13691363
LMArena German13501361
LMArena Japanese12201169
LMArena Korean12631232
LMArena Russian13301359
LMArena Spanish13541354

Instruction Following MiniMax-M2.5 leads

MiniMax M1: 69.5 (#169), MiniMax-M2.5: 71.7 (#143)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Instruction Following13121353

Long Context MiniMax M1 leads

MiniMax M1: 41.4 (#136), MiniMax-M2.5: 37.4 (#211)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Longer Query13261367
Fiction.LiveBench69.4%—
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference Too close to call

MiniMax M1: 53.3 (#155), MiniMax-M2.5: 54.1 (#149)

BenchmarkMiniMax M1MiniMax-M2.5
LMArena Text13431359
LMArena Creative Writing12981331
LMArena Multi-Turn13351364
EQ-Bench Creative Writing—1361

Frequently asked questions

Is MiniMax M1 better than MiniMax-M2.5?

MiniMax M1 is the stronger model overall, scoring 39.7 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 1.6× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.

Which is cheaper, MiniMax M1 or MiniMax-M2.5?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax M1 lists at $0.40 and $2.20.

Is MiniMax M1 or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 39.2 in the Noometry coding category.

Which has the bigger context window?

MiniMax M1 does, with 1M tokens against 205K.

How many benchmarks do MiniMax M1 and MiniMax-M2.5 share?

17 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper