NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GLM 5
z-ai logo

GLM 5

by z-ai · Released Feb 2026

Open Source
64.1
avg score
Rank #63
Compare
Better than 80% of all models
Context
205K tokens (~102 books)
Input $/1M
$0.60
Output $/1M
$1.92
Type
text
License
Open Source
Benchmarks
30 tested
Data as of
About

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Tested on 30 benchmarks · BenchGecko score 64.1. Top scores: Chatbot Arena Elo — Overall (1457.6%), Chatbot Arena Elo — Coding (1434.0%), OpenCompass — AIME2025 (95.8%).

Capabilities
coding
64.6
#34 globally
reasoning
46.1
#87 globally
math
55.6
#100 globally
knowledge
53.6
#99 globally
agentic
17.2
#51 globally
language
75.4
#66 globally
general
18.7
#166 globally
Benchmark Scores
Compare All
Tested on 30 benchmarks · Ranked across 8 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
OpenCompass — LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

86.2·
LiveBench — Coding

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

73.6·
SWE-Bench verified

Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.

72.1·
reasoningCompare reasoning →
LiveBench — Reasoning

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

69.1·
LiveBench — Data Analysis

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

67.9·
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

44.7·
mathCompare math →
OpenCompass — AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

95.8·
LiveBench — Mathematics

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

83.5·
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

80.0·
Quick compare:Alibaba logovs Qwen2.5 Coder 14B InstructMeta logovs Meta Llama 3 8BTII logovs Falcon 2 11B
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · z-ai GLM 5
Feb 2026
64.1
$0.60/M in205Kctx30 benchmarks
Mar 2026
$1.20/M in(+0.60)203Kctx(-2K)3 benchmarks
See the full GLM 5 family →
Recently Happened
GLM 5 pricing dropped 37%
Aug 15, 2026
GLM 5 pricing dropped 8%
May 6, 2026
GLM 5 pricing dropped 8%
Apr 24, 2026
GLM 5 pricing dropped 10%
Apr 22, 2026
Similar Models
Alibaba logo
Qwen2.5 Coder 14B Instruct
Alibaba
64.1n/a
Meta logo
Meta Llama 3 8B
Meta
64.0n/a
TII logo
Falcon 2 11B
TII
64.3n/a
Links
Info
z-aiPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@z-ai
Source Code
GitHubHugging Face
BenchGecko API
glm-5
Specifications
  • Typetext
  • Context205K tokens (~102 books)
  • ReleasedFeb 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.003
Available On
z-ai logoz-ai$0.60
Categories
codingreasoningmathknowledgeagenticlanguagegeneral
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba logoQwen2.5 Coder 14B Instruct
64.1
Meta logoMeta Llama 3 8B
64.0
TII logoFalcon 2 11B
64.3
OpenAI logoGPT-4 (older v0314)
63.8
GLM 5 is an open-source text AI model by z-ai, released in February 2026. It has an average benchmark score of 64.1. Context window: 205K tokens.

Related Models

Qwen2.5 Coder 14B Instruct · AlibabaMeta Llama 3 8B · MetaFalcon 2 11B · TIIGPT-4 (older v0314) · OpenAIGLM 5.1 · z-ai

Benchmarks

Chatbot Arena Elo — OverallChatbot Arena Elo — CodingOpenCompass — AIME2025OpenCompass — IFEvalOpenCompass — LiveCodeBenchV6

Related Pages

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

Key facts · as of 2026-10-05

  • GLM 5 by z-ai. BenchGecko score 64.1, rank 63 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.60 input · $1.92 output per 1M tokens (as of 2026-10-05).
  • Sold by 8 providers (as of 2026-10-05): GMICloud (fp8) $0.60 in / $1.92 out · StreamLake (fp8) $0.60 in / $1.92 out · Baidu (fp8) $0.70 in / $2.24 out · SiliconFlow (fp8) $0.95 in / $2.55 out · Amazon Bedrock $1.00 in / $3.20 out · and 3 more. Every provider

How to cite · data as of 2026-10-05

GLM 5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/glm-5

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