Noometry

Model comparison

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

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 33.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

MiMo-V2.5 Xiaomi

43.4

Rank #93 Confirmed

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

33.4

Rank #245 Confirmed

Summary

  • They share 12 benchmarks with published results for both. MiMo-V2.5 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where MiMo-V2.5 leads 43.9 to 22.6.
  • MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
  • MiMo-V2.5 accepts more context: 1.05M tokens versus 33K.

Side by side

MiMo-V2.5Qwen2.5-Coder-32B
ProviderXiaomiAlibaba (Qwen)
Noometry Index43.433.4
Released2026-04-222024-09-18
WeightsOpenOpen
Context window1.05M33K
Max output131K29K
Input $ / M tokens$0.14$0.66
Output $ / M tokens$0.28$1
Results tracked2331

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

Category by category

Coding MiMo-V2.5 leads

MiMo-V2.5: 43.9 (#81), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Coding14691276
SWE-bench Verified (bash only)—9%
Aider Polyglot—16.4%
LMArena WebDev1438—
SciCode43.1%—
BigCodeBench Instruct—49%
LiveBench Coding—56.9%
BigCodeBench Complete—58%
ALE-Bench513.95—
HumanEval+—87.2%
MBPP+—77%

Reasoning MiMo-V2.5 leads

MiMo-V2.5: 28.6 (#101), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Hard Prompts14501251
CritPt3.7%—
LiveBench Reasoning—42.1%
LiveBench Data Analysis—49.9%
Epoch Capabilities Index—119.49
HellaSwag—83%
LiveBench—46.2%
WinoGrande—80.8%

Math MiMo-V2.5 leads

MiMo-V2.5: 36.8 (#163), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Math14361251
ProofBench16%—
LiveBench Math—46.6%
GSM8K—93%

Knowledge MiMo-V2.5 leads

MiMo-V2.5: 40.8 (#115), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Expert14601221
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multimodal Not comparable

MiMo-V2.5: 39.8 (#54), Qwen2.5-Coder-32B: —

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Vision1247—

Multilingual MiMo-V2.5 leads

MiMo-V2.5: 51.9 (#99), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Non-English14041205
LMArena Chinese14681222
LMArena Russian13951228
LMArena French1447—
LMArena German1421—
LMArena Japanese1306—
LMArena Korean1363—
LMArena Spanish1416—

Instruction Following MiMo-V2.5 leads

MiMo-V2.5: 75.5 (#60), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Instruction Following14341223
LiveBench Instruction Following—58.7%

Long Context MiMo-V2.5 leads

MiMo-V2.5: 44.2 (#73), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Longer Query14451251

Writing & Preference MiMo-V2.5 leads

MiMo-V2.5: 61.6 (#86), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkMiMo-V2.5Qwen2.5-Coder-32B
LMArena Text14281230
LMArena Creative Writing13931174
LMArena Multi-Turn14451222
LiveBench Language—23.3%

Frequently asked questions

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

MiMo-V2.5 is the stronger model overall, scoring 43.4 to 33.4 on the Noometry Index.

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

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

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

MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 33K.

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

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

Related comparisons

Go deeper