NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GLM 4.6V
z-ai logo

GLM 4.6V

by z-ai · Released Dec 2025

Open SourceMultimodal
27.7
avg score
Rank #271
Compare
Better than 17% of all models
Context
131K tokens (~66 books)
Input $/1M
$0.30
Output $/1M
$0.90
Type
multimodal
License
Open Source
Benchmarks
9 tested
Data as of
About

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

Tested on 9 benchmarks · BenchGecko score 27.7. Top scores: Chatbot Arena Elo · Overall (1378.7%), LiveBench · Coding (64.2%), LiveBench · Mathematics (62.5%).

Looking for similar performance at lower cost?
Llama 3.3 70B Instruct (free) scores 28.7 (104% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
33.8
#166 globally
reasoning
41.8
#112 globally
math
62.5
#88 globally
knowledge
40.1
#219 globally
language
33.4
#141 globally
Benchmark Scores
Compare All
Tested on 9 benchmarks · Ranked across 6 categories
Score Distribution (all 326 models)
0255075100
▲ You are here
codingCompare coding →
LiveBench · Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

64.2·
LiveBench · Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

3.3·
reasoningCompare reasoning →
LiveBench · Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

46.4·
LiveBench · Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

37.2·
mathCompare math →
LiveBench · Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

62.5·
Quick compare:Anthropic logovs Claude 3 OpusOpenAI logovs GPT-4o-miniDeepSeek logovs DeepSeek Coder 33B
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
Anthropic logo
Claude 3 Opus
Anthropic
27.9n/a
OpenAI logo
GPT-4o-mini
OpenAI
27.4$0.15/1M
DeepSeek logo
DeepSeek Coder 33B
DeepSeek
27.3n/a
Links
Info
z-aiPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@z-ai
Source Code
GitHubHugging Face
BenchGecko API
glm-4-6v
Specifications
  • Typemultimodal
  • Context131K tokens (~66 books)
  • ReleasedDec 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.002
Available On
z-ai logoz-ai$0.30
Categories
codingreasoningmathknowledgelanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
Anthropic logoClaude 3 Opus
27.9
OpenAI logoGPT-4o-mini
27.4
DeepSeek logoDeepSeek Coder 33B
27.3
OpenAI logoGPT-5.4 Nano
28.5
GLM 4.6V is an open-source multimodal AI model by z-ai, released in December 2025. It has an average benchmark score of 27.7. Context window: 131K tokens.

Related Models

Claude 3 Opus · AnthropicGPT-4o-mini · OpenAIDeepSeek Coder 33B · DeepSeekGPT-5.4 Nano · OpenAIQwen2.5 1.5B Instruct · Alibaba

Benchmarks

Chatbot Arena Elo · OverallLiveBench · CodingLiveBench · MathematicsLiveBench · LanguageLiveBench · Data Analysis

Related Pages

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

Key facts · as of 2026-11-11

  • GLM 4.6V by z-ai. BenchGecko score 27.7, rank 271 of 326 scored models (normalized average of public benchmark scores).
  • List price $0.30 input · $0.90 output per 1M tokens (as of 2026-11-11).
  • Sold by 2 providers (as of 2026-11-11): Novita (bf16) $0.30 in / $0.90 out · Z.AI (fp8) $0.30 in / $0.90 out. Every provider

How to cite · data as of 2026-11-11

GLM 4.6V · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/glm-4-6v

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