Noometry

Model comparison

GLM-4.5-Air vs Qwen2.5 7B Instruct

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.0 on the Noometry Index.

Last verified . 5 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • They share 5 benchmarks with published results for both. GLM-4.5-Air scores higher in 5 categories and Qwen2.5 7B Instruct in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.5-Air leads 36.2 to 12.6.
  • The biggest single-benchmark swing is GPQA (HELM): 59.4% for GLM-4.5-Air and 34.1% for Qwen2.5 7B Instruct.
  • Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.

Side by side

GLM-4.5-AirQwen2.5 7B Instruct
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index38.929.0
Released2025-07-202024-09
WeightsOpenOpen
Context window131K131K
Max output98K8K
Input $ / M tokens$0.20$0.17
Output $ / M tokens$1.10$0.70
Results tracked2715

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

Category by category

Coding Qwen2.5 7B Instruct leads

GLM-4.5-Air: 33.3 (#259), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
GSO2.9%—
BigCodeBench Instruct—37.6%
LMArena Coding1397—
BigCodeBench Complete—46.1%

Agentic & Tool Use Not comparable

GLM-4.5-Air: —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
BALROG—7.8%

Reasoning GLM-4.5-Air leads

GLM-4.5-Air: 24.1 (#166), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
Kagi LLM Benchmark43%—
Chess Puzzles—0%
LMArena Hard Prompts1379—
DTBench—47.7%
LMCA—6.4%
Epoch Capabilities Index—118.51
ForecastBench59.2—

Math GLM-4.5-Air leads

GLM-4.5-Air: 36.2 (#170), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
Omni-MATH39.1%29.4%
OTIS Mock AIME 2024-2025—2.5%
LMArena Math1396—

Knowledge GLM-4.5-Air leads

GLM-4.5-Air: 35.0 (#191), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
MMLU-Pro76.2%53.9%
GPQA (HELM)59.4%34.1%
GPQA Diamond—35.5%
Humanity's Last Exam8.1%—
Vectara Hallucination Rate9.3%—
LMArena Expert1370—
MMLU—72.9%

Multilingual Not comparable

GLM-4.5-Air: 49.1 (#135), Qwen2.5 7B Instruct: —

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
LMArena Non-English1366—
LMArena Chinese1426—
LMArena French1399—
LMArena German1377—
LMArena Japanese1348—
LMArena Korean1308—
LMArena Russian1373—
LMArena Spanish1386—

Instruction Following GLM-4.5-Air leads

GLM-4.5-Air: 69.6 (#171), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
IFEval81.2%74.1%
LMArena Instruction Following1354—

Long Context Not comparable

GLM-4.5-Air: 41.6 (#135), Qwen2.5 7B Instruct: —

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
LMArena Longer Query1366—

Writing & Preference GLM-4.5-Air leads

GLM-4.5-Air: 55.9 (#139), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkGLM-4.5-AirQwen2.5 7B Instruct
WildBench78.9%73.1%
LMArena Text1384—
LMArena Creative Writing1343—
LMArena Multi-Turn1371—

Frequently asked questions

Is GLM-4.5-Air better than Qwen2.5 7B Instruct?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.0 on the Noometry Index.

Which is cheaper, GLM-4.5-Air or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.

Is GLM-4.5-Air or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 33.3 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do GLM-4.5-Air and Qwen2.5 7B Instruct share?

5 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper