GLM 5 Original
GLM-5 is a capable open-weight model from Zhipu with advanced reasoning and instruction following. This Original variant uses the model maker's direct endpoint.
- Reasoning
- Tool Calling
- Structured Output
Added Feb 11, 2026
Pricing
Auto routing · per 1M tokens- Input
- $0.60
- Output
- $1.90
- Cache read
- $0.10
Specifications
- Context window
- 200K
- Max output
- 128K
- Parameters
- 744B / 40B
- Total / active
- Avg output (7d)
- 313 tokens
- Longer than 27% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
27.9
Agentic work
T²-Bench Telecom (legacy)
Legacy fallback · Conversational AI agents in dual-control scenarios
98.2%
Better than 98% of models compared
Document reasoning
AA-LCR v1.1
Long context reasoning with updated grading
75.7%
Better than 74% of models compared
Reasoning
HLE
Humanity's Last Exam
29.3%
Better than 77% of models compared
IFBench
Instruction-following benchmark
72.3%
Better than 89% of models compared
CritPt
Research-level physics reasoning
0.0%
Coding
Terminal-Bench Hard (legacy)
Legacy fallback · Agentic coding and terminal use
43.2%
Better than 90% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
23.1%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
45.3%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
82.0%
Better than 70% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
75.7%
Better than 74% of models compared
Last updated Oct 9, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…