Noometry

Model comparison

MiMo-V2-Pro vs Qwen3.5 27B

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 41.9 on the Noometry Index.

Last verified . 21 shared benchmarks.

MiMo-V2-Pro Xiaomi

43.0

Rank #103 Confirmed

Qwen3.5 27B Alibaba (Qwen)

41.9

Rank #127 Confirmed

Summary

  • They share 21 benchmarks with published results for both. MiMo-V2-Pro scores higher in 6 categories and Qwen3.5 27B in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Qwen3.5 27B leads 27.5 to 22.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 25.8% for MiMo-V2-Pro and 47.9% for Qwen3.5 27B.
  • MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.30 / $2.40 for Qwen3.5 27B.
  • MiMo-V2-Pro accepts more context: 1.05M tokens versus 262K.
  • Qwen3.5 27B has downloadable open weights; the other is API-only.

Side by side

MiMo-V2-ProQwen3.5 27B
ProviderXiaomiAlibaba (Qwen)
Noometry Index43.041.9
Released2026-03-182026-02-23
WeightsProprietaryOpen
Context window1.05M262K
Max output131K66K
Input $ / M tokens$0.43$0.30
Output $ / M tokens$0.87$2.40
Results tracked2328

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

Category by category

Coding MiMo-V2-Pro leads

MiMo-V2-Pro: 43.8 (#83), Qwen3.5 27B: 38.9 (#168)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena WebDev14331358
LMArena Coding14761427
ALE-Bench785.17349.45
WeirdML—39.5%

Agentic & Tool Use Not comparable

MiMo-V2-Pro: —, Qwen3.5 27B: —

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

Reasoning Qwen3.5 27B leads

MiMo-V2-Pro: 22.1 (#206), Qwen3.5 27B: 27.5 (#117)

BenchmarkMiMo-V2-ProQwen3.5 27B
NYT Connections (extended)25.8%47.9%
Thematic Generalization45.9%45.5%
LMArena Hard Prompts14571414
DTBench—82.4%
LMCA—34%

Math Too close to call

MiMo-V2-Pro: 39.5 (#102), Qwen3.5 27B: 38.8 (#127)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Math14471429
MathArena Final-Answer Competitions—56.7%

Knowledge MiMo-V2-Pro leads

MiMo-V2-Pro: 41.4 (#111), Qwen3.5 27B: 38.0 (#150)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Expert14781428
Vectara Hallucination Rate—12.1%

Multimodal Not comparable

MiMo-V2-Pro: —, Qwen3.5 27B: 39.4 (#59)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Vision—1241

Multilingual MiMo-V2-Pro leads

MiMo-V2-Pro: 52.7 (#81), Qwen3.5 27B: 50.8 (#115)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Non-English14161390
LMArena Chinese14561478
LMArena French14691410
LMArena German14171393
LMArena Japanese13661345
LMArena Korean14001358
LMArena Russian14271390
LMArena Spanish14571407

Instruction Following MiMo-V2-Pro leads

MiMo-V2-Pro: 76.0 (#49), Qwen3.5 27B: 73.5 (#119)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Instruction Following14451393

Long Context Qwen3.5 27B leads

MiMo-V2-Pro: 41.5 (#138), Qwen3.5 27B: 43.1 (#106)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Longer Query14551413
CL-bench15.7%—
CL-bench Life6.9%—

Writing & Preference MiMo-V2-Pro leads

MiMo-V2-Pro: 62.8 (#70), Qwen3.5 27B: 59.3 (#111)

BenchmarkMiMo-V2-ProQwen3.5 27B
LMArena Text14361409
LMArena Creative Writing14151362
LMArena Multi-Turn14561410

Frequently asked questions

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

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 41.9 on the Noometry Index.

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

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

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 38.9 in the Noometry coding category.

Which has the bigger context window?

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

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

21 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen3.5 27B has 28.

Related comparisons

Go deeper