NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GLM 4 32B
z-ai logo

GLM 4 32B

by z-ai · Released Jul 2025

37.5
avg score
Rank #209
Compare
Better than 33% of all models
Context
128K tokens (~64 books)
Input $/1M
$0.10
Output $/1M
$0.10
Type
text
License
Proprietary
Benchmarks
6 tested
Data as of
About

GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks. It...

Tested on 6 benchmarks · BenchGecko score 37.5. Top scores: BBH (HuggingFace) (35.8%), MMLU-PRO (34.9%), IFEval (14.3%).

Looking for similar performance at lower cost?
GPT-5 Nano scores 37.7 (101% as good) at $0.05/1M input · 50% cheaper
Capabilities
reasoning
14.2
#153 globally
math
0.0
#289 globally
knowledge
21.9
#261 globally
general
35.8
#94 globally
language
14.3
#171 globally
Benchmark Scores
Compare All
Tested on 6 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

14.2·
mathCompare math →
MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

0.0·
knowledgeCompare knowledge →
MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

34.9·
GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

8.8·
Quick compare:Google DeepMind logovs Gemini 2.5 FlashAnthropic logovs Claude 2Mistral AI logovs Mistral Medium 3
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · z-ai GLM 4
Jul 2025
37.5
$0.10/M in128Kctx6 benchmarks
Aug 2025
$0.60/M in(+0.50)66Kctx(-62K)1 benchmark
Dec 2025
27.7-9.8
$0.30/M in(-0.30)131Kctx(+66K)9 benchmarks
See the full GLM 4 family →
Similar Models
Google DeepMind logo
Gemini 2.5 Flash
Google DeepMind
37.3$0.30/1M
Anthropic logo
Claude 2
Anthropic
37.7n/a
Mistral AI logo
Mistral Medium 3
Mistral AI
37.3$0.40/1M
Links
Info
z-aiPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@z-ai
BenchGecko API
glm-4-32b
Specifications
  • Typetext
  • Context128K tokens (~64 books)
  • ReleasedJul 2025
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.000
Available On
z-ai logoz-ai$0.10
Categories
reasoningmathknowledgegenerallanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Google DeepMind logoGemini 2.5 Flash
37.3
Anthropic logoClaude 2
37.7
Mistral AI logoMistral Medium 3
37.3
OpenAI logoGPT-5 Nano
37.7
GLM 4 32B is a proprietary text AI model by z-ai, released in July 2025. It has an average benchmark score of 37.5. Context window: 128K tokens.

Related Models

Gemini 2.5 Flash · Google DeepMindClaude 2 · AnthropicMistral Medium 3 · Mistral AIGPT-5 Nano · OpenAIHermes 2 Pro - Llama-3 8B · nousresearch

Benchmarks

BBH (HuggingFace)MMLU-PROIFEvalMUSRGPQA

Related Pages

z-ai · Providerz-ai · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-05-03

  • GLM 4 32B by z-ai. BenchGecko score 37.5, rank 209 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.10 input · $0.10 output per 1M tokens (as of 2026-05-03).

How to cite · data as of 2026-05-03

GLM 4 32B · benchmarks, pricing and providers. BenchGecko, data as of 2026-05-03. https://benchgecko.ai/model/glm-4-32b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP