Noometry

Model comparison

MiniMax-M2.7 vs Qwen2.5 32B Instruct

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 29.7 on the Noometry Index.

Last verified . 1 shared benchmarks.

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Qwen2.5 32B Instruct Alibaba (Qwen)

29.7

Rank #291 Confirmed

Summary

  • They share 1 benchmark with published results for both. MiniMax-M2.7 scores higher in 4 categories and Qwen2.5 32B Instruct in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M2.7 leads 37.1 to 24.9.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
  • MiniMax-M2.7 accepts more context: 205K tokens versus 131K.

Side by side

MiniMax-M2.7Qwen2.5 32B Instruct
ProviderMiniMaxAlibaba (Qwen)
Noometry Index37.429.7
Released2026-03-182024-09
WeightsOpenOpen
Context window205K131K
Max output131K8K
Input $ / M tokens$0.30$0.70
Output $ / M tokens$1.20$2.80
Results tracked307

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

Category by category

Coding MiniMax-M2.7 leads

MiniMax-M2.7: 41.4 (#115), Qwen2.5 32B Instruct: 38.1 (#165)

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
LMArena WebDev1397—
SciCode47%—
WeirdML37%—
BigCodeBench Instruct—45%
LMArena Coding1454—
BigCodeBench Complete—52.3%
ALE-Bench599.25—

Agentic & Tool Use Not comparable

MiniMax-M2.7: 24.9 (#103), Qwen2.5 32B Instruct: —

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
Terminal-Bench45.1%—
ExploitBench13.3%—
GBAEval0%—

Reasoning Too close to call

MiniMax-M2.7: 19.0 (#248), Qwen2.5 32B Instruct: 18.5 (#262)

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
Epoch Capabilities Index145.84128.52
NYT Connections (extended)24.7%—
CritPt0.6%—
Chess Puzzles—0%
Thematic Generalization39.3%—
LMArena Hard Prompts1422—

Math MiniMax-M2.7 leads

MiniMax-M2.7: 24.9 (#254), Qwen2.5 32B Instruct: 15.3 (#289)

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
OTIS Mock AIME 2024-2025—7.4%
ProofBench3%—
LMArena Math1420—
MATH Level 5—56.1%

Knowledge MiniMax-M2.7 leads

MiniMax-M2.7: 37.1 (#151), Qwen2.5 32B Instruct: 24.9 (#259)

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
GPQA Diamond—46.1%
Vectara Hallucination Rate12.9%—
LMArena Expert1443—

Multilingual Not comparable

MiniMax-M2.7: 50.5 (#120), Qwen2.5 32B Instruct: —

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
LMArena Non-English1382—
LMArena Chinese1439—
LMArena French1422—
LMArena German1398—
LMArena Japanese1261—
LMArena Korean1313—
LMArena Russian1383—
LMArena Spanish1403—

Instruction Following Not comparable

MiniMax-M2.7: 74.2 (#101), Qwen2.5 32B Instruct: —

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
LMArena Instruction Following1404—

Long Context Not comparable

MiniMax-M2.7: 43.3 (#94), Qwen2.5 32B Instruct: —

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
LMArena Longer Query1419—

Writing & Preference Not comparable

MiniMax-M2.7: 59.1 (#107), Qwen2.5 32B Instruct: —

BenchmarkMiniMax-M2.7Qwen2.5 32B Instruct
LMArena Text1404—
LMArena Creative Writing1354—
LMArena Multi-Turn1413—

Frequently asked questions

Is MiniMax-M2.7 better than Qwen2.5 32B Instruct?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 29.7 on the Noometry Index.

Which is cheaper, MiniMax-M2.7 or Qwen2.5 32B Instruct?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.

Is MiniMax-M2.7 or Qwen2.5 32B Instruct better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 38.1 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 131K.

How many benchmarks do MiniMax-M2.7 and Qwen2.5 32B Instruct share?

1 benchmark has published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen2.5 32B Instruct has 7.

Related comparisons

Go deeper