Noometry

Model comparison

GLM-4.7 vs Qwen2.5 32B Instruct

GLM-4.7 is the stronger model overall, scoring 42.0 to 30.1 on the Noometry Index.

Last verified . 4 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Qwen2.5 32B Instruct Alibaba (Qwen)

30.1

Rank #297 Confirmed

Summary

  • They share 4 benchmarks with published results for both. GLM-4.7 scores higher in 4 categories and Qwen2.5 32B Instruct in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7 leads 38.6 to 16.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 7.4% for Qwen2.5 32B Instruct.
  • GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.70 / $2.80 for Qwen2.5 32B Instruct.
  • GLM-4.7 accepts more context: 205K tokens versus 131K.

Side by side

GLM-4.7Qwen2.5 32B Instruct
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index42.030.1
Released2025-12-222024-09
WeightsOpenOpen
Context window205K131K
Max output131K8K
Input $ / M tokens$0.60$0.70
Output $ / M tokens$2.20$2.80
Results tracked367

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 44.0 (#79), Qwen2.5 32B Instruct: 38.7 (#169)

BenchmarkGLM-4.7Qwen2.5 32B Instruct
LMArena WebDev1435—
SciCode45.1%—
BigCodeBench Instruct—45%
LMArena Coding1454—
BigCodeBench Complete—52.3%
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.5 (#103), Qwen2.5 32B Instruct: —

BenchmarkGLM-4.7Qwen2.5 32B Instruct
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning GLM-4.7 leads

GLM-4.7: 24.3 (#164), Qwen2.5 32B Instruct: 19.2 (#266)

BenchmarkGLM-4.7Qwen2.5 32B Instruct
Chess Puzzles6%0%
Epoch Capabilities Index143.51128.52
SimpleBench47.7%—
CritPt1.7%—
LMArena Hard Prompts1443—

Math GLM-4.7 leads

GLM-4.7: 38.6 (#135), Qwen2.5 32B Instruct: 16.2 (#296)

BenchmarkGLM-4.7Qwen2.5 32B Instruct
OTIS Mock AIME 2024-202583.3%7.4%
ProofBench6%—
LMArena Math1423—
MATH Level 5—56.1%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#80), Qwen2.5 32B Instruct: 24.9 (#266)

BenchmarkGLM-4.7Qwen2.5 32B Instruct
GPQA Diamond83.3%46.1%
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—
LMArena Expert1424—

Multilingual Not comparable

GLM-4.7: 52.8 (#79), Qwen2.5 32B Instruct: —

BenchmarkGLM-4.7Qwen2.5 32B Instruct
LMArena Non-English1417—
LMArena Chinese1495—
LMArena French1432—
LMArena German1424—
LMArena Japanese1439—
LMArena Korean1399—
LMArena Russian1423—
LMArena Spanish1434—

Instruction Following Not comparable

GLM-4.7: 74.4 (#95), Qwen2.5 32B Instruct: —

BenchmarkGLM-4.7Qwen2.5 32B Instruct
LMArena Instruction Following1411—

Long Context Not comparable

GLM-4.7: 42.8 (#116), Qwen2.5 32B Instruct: —

BenchmarkGLM-4.7Qwen2.5 32B Instruct
CL-bench15.9%—
CL-bench Life10.9%—
LMArena Longer Query1432—

Writing & Preference Not comparable

GLM-4.7: 60.9 (#93), Qwen2.5 32B Instruct: —

BenchmarkGLM-4.7Qwen2.5 32B Instruct
LMArena Text1435—
LMArena Creative Writing1401—
EQ-Bench Creative Writing1413—
LMArena Multi-Turn1446—

Frequently asked questions

Is GLM-4.7 better than Qwen2.5 32B Instruct?

GLM-4.7 is the stronger model overall, scoring 42.0 to 30.1 on the Noometry Index.

Which is cheaper, GLM-4.7 or Qwen2.5 32B Instruct?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen2.5 32B Instruct lists at $0.70 and $2.80.

Is GLM-4.7 or Qwen2.5 32B Instruct better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 38.7 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 131K.

How many benchmarks do GLM-4.7 and Qwen2.5 32B Instruct share?

4 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen2.5 32B Instruct has 7.

Related comparisons

Go deeper