Noometry

Model comparison

MiniMax-M2.1 vs MiniMax-M2.5

MiniMax-M2.1 and MiniMax-M2.5 score almost the same on the Noometry Index (38.4 vs 38.1), so choose on price, context window or the category you care about most.

Last verified . 22 shared benchmarks.

MiniMax-M2.1 MiniMax

38.4

Rank #177 Confirmed

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

Summary

  • They share 22 benchmarks with published results for both. MiniMax-M2.1 scores higher in 5 categories and MiniMax-M2.5 in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2.1 leads 35.6 to 25.8.
  • The biggest single-benchmark swing is Terminal-Bench: 36.6% for MiniMax-M2.1 and 42.7% for MiniMax-M2.5.
  • Both cost about the same: $0.30 input and $1.20 output per million tokens.

Side by side

MiniMax-M2.1MiniMax-M2.5
ProviderMiniMaxMiniMax
Noometry Index38.438.1
Released2025-12-232026-02-12
WeightsOpenOpen
Context window205K205K
Max output131K131K
Input $ / M tokens$0.30$0.30
Output $ / M tokens$1.20$1.20
Results tracked2233

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.1: 40.1 (#132), MiniMax-M2.5: 47.9 (#53)

BenchmarkMiniMax-M2.1MiniMax-M2.5
LMArena WebDev13841386
LMArena Coding14211380
ALE-Bench623.83618.17
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—68.3%

Agentic & Tool Use MiniMax-M2.5 leads

MiniMax-M2.1: 27.7 (#91), MiniMax-M2.5: 30.2 (#70)

BenchmarkMiniMax-M2.1MiniMax-M2.5
Terminal-Bench36.6%42.7%
Vending-Bench 2—-23.16

Reasoning MiniMax-M2.5 leads

MiniMax-M2.1: 15.8 (#301), MiniMax-M2.5: 17.6 (#281)

BenchmarkMiniMax-M2.1MiniMax-M2.5
NYT Connections (extended)11.2%16.8%
LMArena Hard Prompts14101372
ARC-AGI-2—4.9%
Kagi LLM Benchmark—55.2%
ARC-AGI-1—63.7%
Epoch Capabilities Index—146.68

Math MiniMax-M2.1 leads

MiniMax-M2.1: 35.6 (#142), MiniMax-M2.5: 25.8 (#242)

BenchmarkMiniMax-M2.1MiniMax-M2.5
LMArena Math13961378
ProofBench—4%

Knowledge Too close to call

MiniMax-M2.1: 37.7 (#143), MiniMax-M2.5: 38.6 (#132)

BenchmarkMiniMax-M2.1MiniMax-M2.5
Vectara Hallucination Rate11.8%9.1%
LMArena Expert14321378

Multilingual MiniMax-M2.1 leads

MiniMax-M2.1: 50.2 (#123), MiniMax-M2.5: 47.3 (#147)

BenchmarkMiniMax-M2.1MiniMax-M2.5
LMArena Non-English13781338
LMArena Chinese14301392
LMArena French14051363
LMArena German13801361
LMArena Japanese12871169
LMArena Korean12971232
LMArena Russian13861359
LMArena Spanish13961354

Instruction Following MiniMax-M2.1 leads

MiniMax-M2.1: 74.0 (#108), MiniMax-M2.5: 71.7 (#143)

BenchmarkMiniMax-M2.1MiniMax-M2.5
LMArena Instruction Following13991353

Long Context MiniMax-M2.1 leads

MiniMax-M2.1: 43.2 (#98), MiniMax-M2.5: 37.4 (#211)

BenchmarkMiniMax-M2.1MiniMax-M2.5
LMArena Longer Query14161367
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference MiniMax-M2.1 leads

MiniMax-M2.1: 58.5 (#114), MiniMax-M2.5: 54.1 (#149)

BenchmarkMiniMax-M2.1MiniMax-M2.5
LMArena Text13921359
LMArena Creative Writing13621331
LMArena Multi-Turn13961364
EQ-Bench Creative Writing—1361

Frequently asked questions

Is MiniMax-M2.1 better than MiniMax-M2.5?

MiniMax-M2.1 and MiniMax-M2.5 score almost the same on the Noometry Index (38.4 vs 38.1), so choose on price, context window or the category you care about most.

Which is cheaper, MiniMax-M2.1 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-M2.1 lists at $0.30 and $1.20.

Is MiniMax-M2.1 or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 205K tokens.

How many benchmarks do MiniMax-M2.1 and MiniMax-M2.5 share?

22 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper