Noometry

Model comparison

MiMo-V2.5-Pro vs Qwen3.5 27B

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 41.4 on the Noometry Index.

Last verified . 22 shared benchmarks.

MiMo-V2.5-Pro Xiaomi

44.8

Rank #70 Confirmed

Qwen3.5 27B Alibaba (Qwen)

41.4

Rank #127 Confirmed

Summary

  • They share 22 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 7 categories and Qwen3.5 27B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where MiMo-V2.5-Pro leads 47.0 to 38.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 34.4% for MiMo-V2.5-Pro and 47.9% for Qwen3.5 27B.
  • MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.30 / $2.40 for Qwen3.5 27B.
  • MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 262K.

Side by side

MiMo-V2.5-ProQwen3.5 27B
ProviderXiaomiAlibaba (Qwen)
Noometry Index44.841.4
Released2026-04-222026-02-23
WeightsOpenOpen
Context window1.05M262K
Max output131K66K
Input $ / M tokens$0.43$0.30
Output $ / M tokens$0.87$2.40
Results tracked2728

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

Category by category

Coding MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 47.0 (#58), Qwen3.5 27B: 38.6 (#159)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena WebDev14771357
LMArena Coding15021427
ALE-Bench899.8349.45
SciCode50.2%—
WeirdML—39.5%

Agentic & Tool Use Not comparable

MiMo-V2.5-Pro: —, Qwen3.5 27B: —

BenchmarkMiMo-V2.5-ProQwen3.5 27B
Vending-Bench 2—201.98

Reasoning Too close to call

MiMo-V2.5-Pro: 25.9 (#124), Qwen3.5 27B: 26.6 (#116)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
NYT Connections (extended)34.4%47.9%
LMArena Hard Prompts14871414
DTBench84.5%82.4%
LMCA29.5%34%
CritPt4%—
Thematic Generalization—45.5%

Math MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 38.6 (#84), Qwen3.5 27B: 36.8 (#103)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Math14801428
MathArena Final-Answer Competitions—56.7%
ProofBench22%—

Knowledge MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 41.5 (#100), Qwen3.5 27B: 37.4 (#149)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Expert15011428
Vectara Hallucination Rate—12.1%

Multimodal Not comparable

MiMo-V2.5-Pro: —, Qwen3.5 27B: 38.7 (#56)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Vision—1240

Multilingual MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 55.3 (#33), Qwen3.5 27B: 51.0 (#112)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Non-English14491390
LMArena Chinese15071478
LMArena French14891409
LMArena German14551393
LMArena Japanese14181345
LMArena Korean14361359
LMArena Russian14501389
LMArena Spanish14701408

Instruction Following MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 77.6 (#21), Qwen3.5 27B: 73.7 (#114)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Instruction Following14771393

Long Context MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 45.4 (#38), Qwen3.5 27B: 43.1 (#103)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Longer Query14821413

Writing & Preference MiMo-V2.5-Pro leads

MiMo-V2.5-Pro: 65.5 (#47), Qwen3.5 27B: 59.5 (#106)

BenchmarkMiMo-V2.5-ProQwen3.5 27B
LMArena Text14651409
LMArena Creative Writing14401362
LMArena Multi-Turn14771410
EQ-Bench Creative Writing1493—
EQ-Bench 41208—

Frequently asked questions

Is MiMo-V2.5-Pro better than Qwen3.5 27B?

MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 41.4 on the Noometry Index.

Which is cheaper, MiMo-V2.5-Pro or Qwen3.5 27B?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen3.5 27B lists at $0.30 and $2.40.

Is MiMo-V2.5-Pro or Qwen3.5 27B better for coding?

MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 38.6 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 262K.

How many benchmarks do MiMo-V2.5-Pro and Qwen3.5 27B share?

22 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Qwen3.5 27B has 28.

Related comparisons

Go deeper