Noometry

Model comparison

MiniMax-M2.5 vs MiniMax-M2.7

MiniMax-M2.5 and MiniMax-M2.7 score almost the same on the Noometry Index (38.1 vs 37.4), so choose on price, context window or the category you care about most.

Last verified . 24 shared benchmarks.

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Summary

  • They share 24 benchmarks with published results for both. MiniMax-M2.5 scores higher in 4 categories and MiniMax-M2.7 in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 41.4.
  • The biggest single-benchmark swing is NYT Connections (extended): 16.8% for MiniMax-M2.5 and 24.7% for MiniMax-M2.7.
  • Both cost about the same: $0.30 input and $1.20 output per million tokens.

Side by side

MiniMax-M2.5MiniMax-M2.7
ProviderMiniMaxMiniMax
Noometry Index38.137.4
Released2026-02-122026-03-18
WeightsOpenOpen
Context window205K205K
Max output131K131K
Input $ / M tokens$0.30$0.30
Output $ / M tokens$1.20$1.20
Results tracked3330

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.5: 47.9 (#53), MiniMax-M2.7: 41.4 (#115)

BenchmarkMiniMax-M2.5MiniMax-M2.7
LMArena WebDev13861397
LMArena Coding13801454
ALE-Bench618.17599.25
SWE-bench Verified (bash only)75.8%—
SWE-bench Multilingual68.3%—
SciCode—47%
WeirdML—37%

Agentic & Tool Use MiniMax-M2.5 leads

MiniMax-M2.5: 30.2 (#70), MiniMax-M2.7: 24.9 (#103)

BenchmarkMiniMax-M2.5MiniMax-M2.7
Terminal-Bench42.7%45.1%
ExploitBench—13.3%
GBAEval—0%
Vending-Bench 2-23.16—

Reasoning MiniMax-M2.7 leads

MiniMax-M2.5: 17.6 (#281), MiniMax-M2.7: 19.0 (#248)

BenchmarkMiniMax-M2.5MiniMax-M2.7
NYT Connections (extended)16.8%24.7%
LMArena Hard Prompts13721422
Epoch Capabilities Index146.68145.84
ARC-AGI-24.9%—
Kagi LLM Benchmark55.2%—
ARC-AGI-163.7%—
CritPt—0.6%
Thematic Generalization—39.3%

Math Too close to call

MiniMax-M2.5: 25.8 (#242), MiniMax-M2.7: 24.9 (#254)

BenchmarkMiniMax-M2.5MiniMax-M2.7
ProofBench4%3%
LMArena Math13781420

Knowledge MiniMax-M2.5 leads

MiniMax-M2.5: 38.6 (#132), MiniMax-M2.7: 37.1 (#151)

BenchmarkMiniMax-M2.5MiniMax-M2.7
Vectara Hallucination Rate9.1%12.9%
LMArena Expert13781443

Multilingual MiniMax-M2.7 leads

MiniMax-M2.5: 47.3 (#147), MiniMax-M2.7: 50.5 (#120)

BenchmarkMiniMax-M2.5MiniMax-M2.7
LMArena Non-English13381382
LMArena Chinese13921439
LMArena French13631422
LMArena German13611398
LMArena Japanese11691261
LMArena Korean12321313
LMArena Russian13591383
LMArena Spanish13541403

Instruction Following MiniMax-M2.7 leads

MiniMax-M2.5: 71.7 (#143), MiniMax-M2.7: 74.2 (#101)

BenchmarkMiniMax-M2.5MiniMax-M2.7
LMArena Instruction Following13531404

Long Context MiniMax-M2.7 leads

MiniMax-M2.5: 37.4 (#211), MiniMax-M2.7: 43.3 (#94)

BenchmarkMiniMax-M2.5MiniMax-M2.7
LMArena Longer Query13671419
CL-bench11.4%—
CL-bench Life6.3%—

Writing & Preference MiniMax-M2.7 leads

MiniMax-M2.5: 54.1 (#149), MiniMax-M2.7: 59.1 (#107)

BenchmarkMiniMax-M2.5MiniMax-M2.7
LMArena Text13591404
LMArena Creative Writing13311354
LMArena Multi-Turn13641413
EQ-Bench Creative Writing1361—

Frequently asked questions

Is MiniMax-M2.5 better than MiniMax-M2.7?

MiniMax-M2.5 and MiniMax-M2.7 score almost the same on the Noometry Index (38.1 vs 37.4), so choose on price, context window or the category you care about most.

Which is cheaper, MiniMax-M2.5 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.

Is MiniMax-M2.5 or MiniMax-M2.7 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 205K tokens.

How many benchmarks do MiniMax-M2.5 and MiniMax-M2.7 share?

24 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper