Zhipu AI logo

GLM-5

Zhipu AI

GLM-5 is the latest flagship language model by Zhipu AI, representing a major leap in reasoning, coding, mathematics, and agentic capabilities. It features a significantly enhanced architecture with improved long-context understanding and multi-step problem solving.

Key Specifications

Parameters
744.0B
Context
200.0K
Release Date
February 10, 2026
Average Score
73.6%

Timeline

Key dates in the model's history
Announcement
February 10, 2026
Last Update
February 12, 2026
Today
March 25, 2026

Technical Specifications

Parameters
744.0B
Training Tokens
28.5T tokens
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)
-
Output (per 1M tokens)
-
Max Input Tokens
200.0K
Max Output Tokens
128.0K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests
SWE-Bench Verified
Self-reported
78.0%

Other Tests

Specialized benchmarks
τ²-Bench
Self-reported
90.0%
BrowseComp
Self-reported
76.0%
MCP Atlas
Self-reported
68.0%
Terminal-Bench 2.0
Self-reported
56.0%

License & Metadata

License
mit
Announcement Date
February 10, 2026
Last Updated
February 12, 2026

Compare GLM-5

All comparisons

Articles about GLM-5

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.