GLM 5.3 TEE
GLM-5.3 is Z.AI's open-weight reasoning model for complex software engineering, autonomous agents, vulnerability research, and long-horizon tasks. Reasoning is always on; choose low, high, or max reasoning effort (defaults to max). This text-only TEE deployment is verified through the selected provider: Redpill attestation with signed completion receipts or the official Tinfoil SDK's ATC/EHBP verification.
- Reasoning
- Tool Calling
- Parallel Tool Calls
- Structured Output
Added Aug 31, 2026
Model weightsPricing
Auto routing · per 1M tokens- Input
- $1.40
- Output
- $4.40
- Cache read
- $0.26
Specifications
- Context window
- 1M
- Max output
- 131.1K
- Parameters
- 744B / 40B
- Total / active
- Avg output (7d)
- 1.3K tokens
- Longer than 81% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
44.8
Coding Index
74.8
Agentic Index
53.1
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
62.2%
Better than 90% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
29.4%
Better than 43% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1510 Elo
Better than 88% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1653 Elo
Better than 95% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
11.2%
Better than 45% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
79.7%
Better than 85% of models compared
MLCR-AA
Medical long-context reasoning
48.3%
Better than 87% of models compared
Reasoning
HLE
Humanity's Last Exam
42.3%
Better than 90% of models compared
CritPt
Research-level physics reasoning
19.1%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
41.9%
Better than 87% of models compared
SciCode
Python programming for scientific computing
59.0%
Better than 93% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
33.9%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
29.6%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
91.7%
Better than 93% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
79.7%
Better than 84% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
57.5%
Last updated Oct 15, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
