Noometry

Model comparison

GLM-4.5 vs Qwen3 32B

GLM-4.5 is the stronger model overall, scoring 42.0 to 39.2 on the Noometry Index.

Last verified . 15 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Qwen3 32B Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GLM-4.5 scores higher in 5 categories and Qwen3 32B in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-4.5 leads 28.6 to 20.2.
  • The biggest single-benchmark swing is Fiction.LiveBench: 58.3% for GLM-4.5 and 74.2% for Qwen3 32B.
  • GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.

Side by side

GLM-4.5Qwen3 32B
ProviderZ.ai (Zhipu)Alibaba (Qwen)
Noometry Index42.039.2
Released2025-07-272025-04
WeightsOpenOpen
Context window131K131K
Max output98K16K
Input $ / M tokens$0.60$0.70
Output $ / M tokens$2.20$2.80
Results tracked2726

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

Category by category

Coding GLM-4.5 leads

GLM-4.5: 41.4 (#125), Qwen3 32B: 37.7 (#190)

BenchmarkGLM-4.5Qwen3 32B
LMArena Coding14341358
SWE-bench Verified (bash only)54.2%—
Aider Polyglot—40%
SciCode—35.4%
WeirdML40.6%—
ALE-Bench344.82—
AlgoTune1.52—

Agentic & Tool Use Not comparable

GLM-4.5: —, Qwen3 32B: 32.6 (#62)

BenchmarkGLM-4.5Qwen3 32B
Berkeley Function Calling Leaderboard—48.7%

Reasoning GLM-4.5 leads

GLM-4.5: 28.6 (#100), Qwen3 32B: 20.2 (#241)

BenchmarkGLM-4.5Qwen3 32B
Kagi LLM Benchmark57.9%54.9%
LMArena Hard Prompts14291334
CritPt—0.3%
Chess Puzzles—5%
DTBench—67.5%
LMCA—17.3%
Epoch Capabilities Index—138.51

Math Too close to call

GLM-4.5: 39.0 (#116), Qwen3 32B: 39.7 (#99)

BenchmarkGLM-4.5Qwen3 32B
LMArena Math14271399
OTIS Mock AIME 2024-2025—66.9%

Knowledge Qwen3 32B leads

GLM-4.5: 35.9 (#179), Qwen3 32B: 40.0 (#125)

BenchmarkGLM-4.5Qwen3 32B
LMArena Expert14331362
GPQA Diamond—65.7%
Humanity's Last Exam8.3%—
Confabulations11.3%—
Vectara Hallucination Rate—5.9%

Multilingual GLM-4.5 leads

GLM-4.5: 52.8 (#77), Qwen3 32B: 45.6 (#167)

BenchmarkGLM-4.5Qwen3 32B
LMArena Non-English14171317
LMArena Chinese14651357
LMArena German14071341
LMArena Russian14141311
LMArena French1418—
LMArena Japanese1415—
LMArena Korean1380—
LMArena Spanish1454—

Instruction Following GLM-4.5 leads

GLM-4.5: 74.1 (#104), Qwen3 32B: 68.9 (#179)

BenchmarkGLM-4.5Qwen3 32B
LMArena Instruction Following14041305

Long Context Qwen3 32B leads

GLM-4.5: 38.2 (#201), Qwen3 32B: 43.8 (#87)

BenchmarkGLM-4.5Qwen3 32B
Fiction.LiveBench58.3%74.2%
LMArena Longer Query14121327

Writing & Preference GLM-4.5 leads

GLM-4.5: 57.5 (#127), Qwen3 32B: 52.9 (#163)

BenchmarkGLM-4.5Qwen3 32B
LMArena Text14301340
LMArena Creative Writing13951297
LMArena Multi-Turn14151331
Short-Story Creative Writing73.4%—
EQ-Bench Creative Writing1343—

Frequently asked questions

Is GLM-4.5 better than Qwen3 32B?

GLM-4.5 is the stronger model overall, scoring 42.0 to 39.2 on the Noometry Index.

Which is cheaper, GLM-4.5 or Qwen3 32B?

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is GLM-4.5 or Qwen3 32B better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 37.7 in the Noometry coding category.

Which has the bigger context window?

Both accept 131K tokens.

How many benchmarks do GLM-4.5 and Qwen3 32B share?

15 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper