Noometry

Model comparison

MiMo-V2-Pro vs MiniMax-M2.5

MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 38.1 on the Noometry Index.

Last verified . 22 shared benchmarks.

MiMo-V2-Pro Xiaomi

42.4

Rank #102 Confirmed

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

Summary

  • They share 22 benchmarks with published results for both. MiMo-V2-Pro scores higher in 7 categories and MiniMax-M2.5 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiMo-V2-Pro leads 36.7 to 25.8.
  • The biggest single-benchmark swing is NYT Connections (extended): 25.8% for MiMo-V2-Pro and 16.8% for MiniMax-M2.5.
  • Both cost about the same: $0.43 input and $0.87 output per million tokens.
  • MiMo-V2-Pro accepts more context: 1.05M tokens versus 205K.
  • MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

MiMo-V2-ProMiniMax-M2.5
ProviderXiaomiMiniMax
Noometry Index42.438.1
Released2026-03-182026-02-12
WeightsProprietaryOpen
Context window1.05M205K
Max output131K131K
Input $ / M tokens$0.43$0.30
Output $ / M tokens$0.87$1.20
Results tracked2333

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

Category by category

Coding MiniMax-M2.5 leads

MiMo-V2-Pro: 43.4 (#76), MiniMax-M2.5: 47.9 (#53)

BenchmarkMiMo-V2-ProMiniMax-M2.5
LMArena WebDev14331386
LMArena Coding14761380
ALE-Bench785.17618.17
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—68.3%

Agentic & Tool Use Not comparable

MiMo-V2-Pro: —, MiniMax-M2.5: 30.2 (#70)

BenchmarkMiMo-V2-ProMiniMax-M2.5
Terminal-Bench—42.7%
Vending-Bench 2—-23.16

Reasoning MiMo-V2-Pro leads

MiMo-V2-Pro: 21.3 (#200), MiniMax-M2.5: 17.6 (#281)

BenchmarkMiMo-V2-ProMiniMax-M2.5
NYT Connections (extended)25.8%16.8%
LMArena Hard Prompts14571372
ARC-AGI-2—4.9%
Kagi LLM Benchmark—55.2%
ARC-AGI-1—63.7%
Thematic Generalization45.9%—
Epoch Capabilities Index—146.68

Math MiMo-V2-Pro leads

MiMo-V2-Pro: 36.7 (#104), MiniMax-M2.5: 25.8 (#242)

BenchmarkMiMo-V2-ProMiniMax-M2.5
LMArena Math14471378
ProofBench—4%

Knowledge MiMo-V2-Pro leads

MiMo-V2-Pro: 40.8 (#106), MiniMax-M2.5: 38.6 (#132)

BenchmarkMiMo-V2-ProMiniMax-M2.5
LMArena Expert14791378
Vectara Hallucination Rate—9.1%

Multilingual MiMo-V2-Pro leads

MiMo-V2-Pro: 52.9 (#77), MiniMax-M2.5: 47.3 (#147)

BenchmarkMiMo-V2-ProMiniMax-M2.5
LMArena Non-English14161338
LMArena Chinese14551392
LMArena French14701363
LMArena German14171361
LMArena Japanese13661169
LMArena Korean14011232
LMArena Russian14271359
LMArena Spanish14581354

Instruction Following MiMo-V2-Pro leads

MiMo-V2-Pro: 76.2 (#46), MiniMax-M2.5: 71.7 (#143)

BenchmarkMiMo-V2-ProMiniMax-M2.5
LMArena Instruction Following14441353

Long Context MiMo-V2-Pro leads

MiMo-V2-Pro: 41.5 (#133), MiniMax-M2.5: 37.4 (#211)

BenchmarkMiMo-V2-ProMiniMax-M2.5
CL-bench15.7%11.4%
CL-bench Life6.9%6.3%
LMArena Longer Query14551367

Writing & Preference MiMo-V2-Pro leads

MiMo-V2-Pro: 62.9 (#67), MiniMax-M2.5: 54.1 (#149)

BenchmarkMiMo-V2-ProMiniMax-M2.5
LMArena Text14361359
LMArena Creative Writing14151331
LMArena Multi-Turn14561364
EQ-Bench Creative Writing—1361

Frequently asked questions

Is MiMo-V2-Pro better than MiniMax-M2.5?

MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 38.1 on the Noometry Index.

Which is cheaper, MiMo-V2-Pro 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; MiMo-V2-Pro lists at $0.43 and $0.87.

Is MiMo-V2-Pro or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 43.4 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 205K.

How many benchmarks do MiMo-V2-Pro and MiniMax-M2.5 share?

22 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper