Noometry

Model comparison

GLM-4.7 vs Qwen Turbo

GLM-4.7 is the stronger model overall, scoring 41.7 to 26.8 on the Noometry Index. Qwen Turbo costs 11× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Last verified . 2 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

Qwen Turbo Alibaba (Qwen)

26.8

Rank #329 Reported

Summary

  • They share 2 benchmarks with published results for both. GLM-4.7 scores higher in 2 categories and Qwen Turbo in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 22.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.3% for GLM-4.7 and 6.1% for Qwen Turbo.
  • Qwen Turbo is cheaper at $0.05 / $0.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • Qwen Turbo accepts more context: 1M tokens versus 205K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7Qwen Turbo
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index41.726.8
Released2025-12-222024-11-01
WeightsOpenProprietary
Context window205K1M
Max output131K16K
Input $ / M tokens$0.60$0.05
Output $ / M tokens$2.20$0.20
Results tracked363

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

Category by category

Coding Not comparable

GLM-4.7: 43.6 (#74), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
LMArena WebDev1435—
SciCode45.1%—
LMArena Coding1454—
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.4 (#96), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning Not comparable

GLM-4.7: 23.7 (#161), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
SimpleBench47.7%—
CritPt1.7%—
Chess Puzzles6%—
LMArena Hard Prompts1443—
Epoch Capabilities Index143.53—

Math GLM-4.7 leads

GLM-4.7: 37.7 (#92), Qwen Turbo: 14.5 (#291)

BenchmarkGLM-4.7Qwen Turbo
OTIS Mock AIME 2024-202583.3%6.1%
ProofBench6%—
LMArena Math1423—
MATH Level 5—56.2%
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#74), Qwen Turbo: 22.2 (#267)

BenchmarkGLM-4.7Qwen Turbo
GPQA Diamond83.3%41.8%
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—
LMArena Expert1424—

Multilingual Not comparable

GLM-4.7: 53.0 (#75), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
LMArena Non-English1417—
LMArena Chinese1495—
LMArena French1432—
LMArena German1426—
LMArena Japanese1439—
LMArena Korean1401—
LMArena Russian1423—
LMArena Spanish1433—

Instruction Following Not comparable

GLM-4.7: 74.6 (#90), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
LMArena Instruction Following1411—

Long Context Not comparable

GLM-4.7: 42.8 (#111), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
CL-bench15.9%—
CL-bench Life10.9%—
LMArena Longer Query1432—

Writing & Preference Not comparable

GLM-4.7: 61.1 (#89), Qwen Turbo: —

BenchmarkGLM-4.7Qwen Turbo
LMArena Text1436—
LMArena Creative Writing1401—
EQ-Bench Creative Writing1413—
LMArena Multi-Turn1446—

Frequently asked questions

Is GLM-4.7 better than Qwen Turbo?

GLM-4.7 is the stronger model overall, scoring 41.7 to 26.8 on the Noometry Index. Qwen Turbo costs 11× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Which is cheaper, GLM-4.7 or Qwen Turbo?

Qwen Turbo is cheaper. It lists at $0.05 per million input tokens and $0.20 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Which has the bigger context window?

Qwen Turbo does, with 1M tokens against 205K.

How many benchmarks do GLM-4.7 and Qwen Turbo share?

2 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Qwen Turbo has 3.

Related comparisons

Go deeper