Noometry

Model comparison

MiMo-V2-Pro vs Qwen2.5-Coder-32B

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 33.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

MiMo-V2-Pro Xiaomi

43.0

Rank #103 Confirmed

Qwen2.5-Coder-32B Alibaba (Qwen)

33.4

Rank #245 Confirmed

Summary

  • They share 12 benchmarks with published results for both. MiMo-V2-Pro scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 41.6.
  • MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
  • MiMo-V2-Pro accepts more context: 1.05M tokens versus 33K.
  • Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

Side by side

MiMo-V2-ProQwen2.5-Coder-32B
ProviderXiaomiAlibaba (Qwen)
Noometry Index43.033.4
Released2026-03-182024-09-18
WeightsProprietaryOpen
Context window1.05M33K
Max output131K29K
Input $ / M tokens$0.43$0.66
Output $ / M tokens$0.87$1
Results tracked2331

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), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Coding14761276
SWE-bench Verified (bash only)—9%
Aider Polyglot—16.4%
LMArena WebDev1433—
BigCodeBench Instruct—49%
LiveBench Coding—56.9%
BigCodeBench Complete—58%
ALE-Bench785.17—
HumanEval+—87.2%
MBPP+—77%

Reasoning Too close to call

MiMo-V2-Pro: 22.1 (#206), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Hard Prompts14571251
NYT Connections (extended)25.8%—
Thematic Generalization45.9%—
LiveBench Reasoning—42.1%
LiveBench Data Analysis—49.9%
Epoch Capabilities Index—119.49
HellaSwag—83%
LiveBench—46.2%
WinoGrande—80.8%

Math MiMo-V2-Pro leads

MiMo-V2-Pro: 39.5 (#102), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Math14471251
LiveBench Math—46.6%
GSM8K—93%

Knowledge MiMo-V2-Pro leads

MiMo-V2-Pro: 41.4 (#111), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Expert14781221
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multilingual MiMo-V2-Pro leads

MiMo-V2-Pro: 52.7 (#81), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Non-English14161205
LMArena Chinese14561222
LMArena Russian14271228
LMArena French1469—
LMArena German1417—
LMArena Japanese1366—
LMArena Korean1400—
LMArena Spanish1457—

Instruction Following MiMo-V2-Pro leads

MiMo-V2-Pro: 76.0 (#49), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Instruction Following14451223
LiveBench Instruction Following—58.7%

Long Context MiMo-V2-Pro leads

MiMo-V2-Pro: 41.5 (#138), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Longer Query14551251
CL-bench15.7%—
CL-bench Life6.9%—

Writing & Preference MiMo-V2-Pro leads

MiMo-V2-Pro: 62.8 (#70), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkMiMo-V2-ProQwen2.5-Coder-32B
LMArena Text14361230
LMArena Creative Writing14151174
LMArena Multi-Turn14561222
LiveBench Language—23.3%

Frequently asked questions

Is MiMo-V2-Pro better than Qwen2.5-Coder-32B?

MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 33.4 on the Noometry Index.

Which is cheaper, MiMo-V2-Pro or Qwen2.5-Coder-32B?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

Is MiMo-V2-Pro or Qwen2.5-Coder-32B better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 33K.

How many benchmarks do MiMo-V2-Pro and Qwen2.5-Coder-32B share?

12 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Qwen2.5-Coder-32B has 31.

Related comparisons

Go deeper