Noometry

Model comparison

GLM-4.5-Air vs Qwen2.5-Coder-32B

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

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

33.4

Rank #245 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GLM-4.5-Air 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 writing & preference, where GLM-4.5-Air leads 55.9 to 41.6.
  • GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
  • GLM-4.5-Air accepts more context: 131K tokens versus 33K.

Side by side

GLM-4.5-AirQwen2.5-Coder-32B
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index38.933.4
Released2025-07-202024-09-18
WeightsOpenOpen
Context window131K33K
Max output98K29K
Input $ / M tokens$0.20$0.66
Output $ / M tokens$1.10$1
Results tracked2731

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

Category by category

Coding GLM-4.5-Air leads

GLM-4.5-Air: 33.3 (#259), Qwen2.5-Coder-32B: 22.6 (#333)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Coding13971276
SWE-bench Verified (bash only)—9%
Aider Polyglot—16.4%
GSO2.9%—
BigCodeBench Instruct—49%
LiveBench Coding—56.9%
BigCodeBench Complete—58%
HumanEval+—87.2%
MBPP+—77%

Reasoning GLM-4.5-Air leads

GLM-4.5-Air: 24.1 (#166), Qwen2.5-Coder-32B: 21.2 (#225)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Hard Prompts13791251
Kagi LLM Benchmark43%—
LiveBench Reasoning—42.1%
LiveBench Data Analysis—49.9%
Epoch Capabilities Index—119.49
ForecastBench59.2—
HellaSwag—83%
LiveBench—46.2%
WinoGrande—80.8%

Math GLM-4.5-Air leads

GLM-4.5-Air: 36.2 (#170), Qwen2.5-Coder-32B: 33.3 (#204)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Math13961251
Omni-MATH39.1%—
LiveBench Math—46.6%
GSM8K—93%

Knowledge GLM-4.5-Air leads

GLM-4.5-Air: 35.0 (#191), Qwen2.5-Coder-32B: 33.4 (#203)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Expert13701221
Humanity's Last Exam8.1%—
MMLU-Pro76.2%—
Vectara Hallucination Rate9.3%—
GPQA (HELM)59.4%—
ARC (AI2) Challenge—70.5%
MMLU—79.1%

Multilingual GLM-4.5-Air leads

GLM-4.5-Air: 49.1 (#135), Qwen2.5-Coder-32B: 37.8 (#235)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Non-English13661205
LMArena Chinese14261222
LMArena Russian13731228
LMArena French1399—
LMArena German1377—
LMArena Japanese1348—
LMArena Korean1308—
LMArena Spanish1386—

Instruction Following GLM-4.5-Air leads

GLM-4.5-Air: 69.6 (#171), Qwen2.5-Coder-32B: 61.4 (#245)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Instruction Following13541223
LiveBench Instruction Following—58.7%
IFEval81.2%—

Long Context GLM-4.5-Air leads

GLM-4.5-Air: 41.6 (#135), Qwen2.5-Coder-32B: 38.0 (#208)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Longer Query13661251

Writing & Preference GLM-4.5-Air leads

GLM-4.5-Air: 55.9 (#139), Qwen2.5-Coder-32B: 41.6 (#240)

BenchmarkGLM-4.5-AirQwen2.5-Coder-32B
LMArena Text13841230
LMArena Creative Writing13431174
LMArena Multi-Turn13711222
WildBench78.9%—
LiveBench Language—23.3%

Frequently asked questions

Is GLM-4.5-Air better than Qwen2.5-Coder-32B?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.4 on the Noometry Index.

Which is cheaper, GLM-4.5-Air or Qwen2.5-Coder-32B?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

Is GLM-4.5-Air or Qwen2.5-Coder-32B better for coding?

GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

GLM-4.5-Air does, with 131K tokens against 33K.

How many benchmarks do GLM-4.5-Air and Qwen2.5-Coder-32B share?

12 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Qwen2.5-Coder-32B has 31.

Related comparisons

Go deeper