Z.ai · Open weights
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
- Tools
- Structured output
- Parallel tools
- Input
- Text
- Output
- Text
- Reasoning effort
- low · high · max
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $1.40
- Output
- $4.40
- Cache read
- $0.26
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 131.1K
- Average output (7 days)
- 1.2K tokens
- Longer than 77% of 465 models
Side by side
GLM 5.3 TEE compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM 5.3 TEEZ.aiThis model | GLM 5.2 Thinking TEEZ.aiRemove | |
|---|---|---|
| Provider | Z.ai | Z.ai |
| Discovery tier | Open weights | Open weights |
| Added | Aug 31, 2026 | Jun 16, 2026 |
| Limits | ||
| Context window | 1.05M | 1.05M |
| Max output | 131.07K | 131.07K |
| Average output | 1.2K tokens | 2K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $1.40 | $1.40 |
| Output | $4.40 | $4.40 |
| Cache read | $0.26Best | $0.70 |
| Performance | ||
| Throughput | 48.0 tok/s | — |
| Time to first token | 4.6 s | — |
| Request success (24h) | 99.7%Best | 87.5% |
| Benchmark indexes | ||
| Intelligence Index | 44.8Best | 33.7 |
| Coding Index | 74.8Best | 68.8 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Structured output | Yes | Yes |
| Parallel tools | Yes | No |
| Reasoning effort | low, high, max | low, medium, high, xhigh, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GLM 5.3 TEE
- GLM 5.2 Thinking TEE
Intelligence Index
- GLM 5.3 TEE44.8
- GLM 5.2 Thinking TEE33.7
GLM 5.3 TEE tested at max reasoning effort
GLM 5.3 TEE: Better than 90% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- GLM 5.3 TEE: 74.8Top
- GLM 5.2 Thinking TEE: 68.8
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GLM 5.3 TEE: 62.2%Top
- GLM 5.2 Thinking TEE: 28.4%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GLM 5.3 TEE: 29.4%Top
- GLM 5.2 Thinking TEE: 6.2%
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- GLM 5.3 TEE: 0.3%
- GLM 5.2 Thinking TEE: —
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GLM 5.3 TEE: 1,505 EloTop
- GLM 5.2 Thinking TEE: 1,227 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GLM 5.3 TEE: 1,649 EloTop
- GLM 5.2 Thinking TEE: 1,373 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GLM 5.3 TEE: 11.2%Top
- GLM 5.2 Thinking TEE: 10.4%
AA-LCRv1.1
Reasoning across long documents
- GLM 5.3 TEE: 79.7%Top
- GLM 5.2 Thinking TEE: 78.3%
MLCR-AA
Long-context reasoning over medical records
- GLM 5.3 TEE: 17.2%Top
- GLM 5.2 Thinking TEE: 12.8%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM 5.3 TEE: 42.3%Top
- GLM 5.2 Thinking TEE: 41.1%
GPQA Diamond
Graduate-level science questions
- GLM 5.3 TEE: 91.7%Top
- GLM 5.2 Thinking TEE: 89.5%
IFBench
Following precise output instructions
- GLM 5.3 TEE: —
- GLM 5.2 Thinking TEE: 73.3%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GLM 5.3 TEE: 41.9%Top
- GLM 5.2 Thinking TEE: 1.0%
SciCode
Scientific computing in Python
- GLM 5.3 TEE: 59.0%Top
- GLM 5.2 Thinking TEE: 51.2%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- GLM 5.3 TEE: —
- GLM 5.2 Thinking TEE: 50.8%
τ²-Bench Telecom
Tool use in a customer-support simulation
- GLM 5.3 TEE: —
- GLM 5.2 Thinking TEE: 99.1%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM 5.3 TEE: 79.7%Top
- GLM 5.2 Thinking TEE: 78.3%
Scores from Artificial Analysis, updated Oct 26, 2026. GLM 5.3 TEE was tested at max reasoning effort; compare scores measured at the same effort.Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 48.0 tok/s
- Faster than 35% of 250 models
- Time to first token
- 4.6 s
- Quicker than 40% of 250 models
- Prompt cache hits
- 87.5%
- About $0.40 per 1M input tokens with caching
- Request success (24h)
- 99.7%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "TEE/glm-5.3",
"reasoning_effort": "low",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="TEE/glm-5.3",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Z.ai
Related models
Other Z.ai models, starting with the same family.