Noometry

Model comparison

MiniMax-M2.5 vs Qwen3 32B

MiniMax-M2.5 and Qwen3 32B score almost the same on the Noometry Index (38.1 vs 38.8), so choose on price, context window or the category you care about most.

Last verified . 16 shared benchmarks.

MiniMax-M2.5 MiniMax

38.1

Rank #181 Confirmed

Qwen3 32B Alibaba (Qwen)

38.8

Rank #166 Confirmed

Summary

  • They share 16 benchmarks with published results for both. MiniMax-M2.5 scores higher in 4 categories and Qwen3 32B in 5 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 32B leads 37.9 to 25.8.
  • MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
  • MiniMax-M2.5 accepts more context: 205K tokens versus 131K.

Side by side

MiniMax-M2.5Qwen3 32B
ProviderMiniMaxAlibaba (Qwen)
Noometry Index38.138.8
Released2026-02-122025-04
WeightsOpenOpen
Context window205K131K
Max output131K16K
Input $ / M tokens$0.30$0.70
Output $ / M tokens$1.20$2.80
Results tracked3326

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), Qwen3 32B: 37.3 (#184)

BenchmarkMiniMax-M2.5Qwen3 32B
LMArena Coding13801358
SWE-bench Verified (bash only)75.8%—
Aider Polyglot—40%
LMArena WebDev1386—
SWE-bench Multilingual68.3%—
SciCode—35.4%
ALE-Bench618.17—

Agentic & Tool Use Qwen3 32B leads

MiniMax-M2.5: 30.2 (#70), Qwen3 32B: 32.3 (#58)

BenchmarkMiniMax-M2.5Qwen3 32B
Terminal-Bench42.7%—
Berkeley Function Calling Leaderboard—48.7%
Vending-Bench 2-23.16—

Reasoning Qwen3 32B leads

MiniMax-M2.5: 17.6 (#281), Qwen3 32B: 19.6 (#233)

BenchmarkMiniMax-M2.5Qwen3 32B
Kagi LLM Benchmark55.2%54.9%
LMArena Hard Prompts13721335
Epoch Capabilities Index146.68138.51
ARC-AGI-24.9%—
NYT Connections (extended)16.8%—
ARC-AGI-163.7%—
CritPt—0.3%
Chess Puzzles—5%
DTBench—67.5%
LMCA—17.3%

Math Qwen3 32B leads

MiniMax-M2.5: 25.8 (#242), Qwen3 32B: 37.9 (#89)

BenchmarkMiniMax-M2.5Qwen3 32B
LMArena Math13781399
OTIS Mock AIME 2024-2025—66.9%
ProofBench4%—

Knowledge Qwen3 32B leads

MiniMax-M2.5: 38.6 (#132), Qwen3 32B: 40.0 (#112)

BenchmarkMiniMax-M2.5Qwen3 32B
Vectara Hallucination Rate9.1%5.9%
LMArena Expert13781362
GPQA Diamond—65.7%

Multilingual MiniMax-M2.5 leads

MiniMax-M2.5: 47.3 (#147), Qwen3 32B: 45.8 (#162)

BenchmarkMiniMax-M2.5Qwen3 32B
LMArena Non-English13381317
LMArena Chinese13921357
LMArena German13611341
LMArena Russian13591311
LMArena French1363—
LMArena Japanese1169—
LMArena Korean1232—
LMArena Spanish1354—

Instruction Following MiniMax-M2.5 leads

MiniMax-M2.5: 71.7 (#143), Qwen3 32B: 69.1 (#174)

BenchmarkMiniMax-M2.5Qwen3 32B
LMArena Instruction Following13531305

Long Context Qwen3 32B leads

MiniMax-M2.5: 37.4 (#211), Qwen3 32B: 43.7 (#83)

BenchmarkMiniMax-M2.5Qwen3 32B
LMArena Longer Query13671327
Fiction.LiveBench—74.2%
CL-bench11.4%—
CL-bench Life6.3%—

Writing & Preference MiniMax-M2.5 leads

MiniMax-M2.5: 54.1 (#149), Qwen3 32B: 53.1 (#158)

BenchmarkMiniMax-M2.5Qwen3 32B
LMArena Text13591340
LMArena Creative Writing13311297
LMArena Multi-Turn13641331
EQ-Bench Creative Writing1361—

Frequently asked questions

Is MiniMax-M2.5 better than Qwen3 32B?

MiniMax-M2.5 and Qwen3 32B score almost the same on the Noometry Index (38.1 vs 38.8), so choose on price, context window or the category you care about most.

Which is cheaper, MiniMax-M2.5 or Qwen3 32B?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is MiniMax-M2.5 or Qwen3 32B better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 131K.

How many benchmarks do MiniMax-M2.5 and Qwen3 32B share?

16 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper