Z.ai · Open weights
GLM 5.2 TEE
GLM-5.2 is Z.AI's flagship model for long-horizon tasks and autonomous workflows, with a 1M-token context window. Running inside a TEE (Trusted Execution Environment), with attestation support.
- Reasoning
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $1.40
- Output
- $4.40
- Cache read
- $0.70
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 131.1K
- Average output (7 days)
- 1.5K tokens
- Longer than 85% of 468 models
Side by side
GLM 5.2 TEE compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM 5.2 TEEZ.aiThis model | GLM 5.3Z.aiRemove | |
|---|---|---|
| Provider | Z.ai | Z.ai |
| Discovery tier | Open weights | Open weights |
| Added | Jun 16, 2026 | Aug 14, 2026 |
| Limits | ||
| Context window | 1.05M | 1.05M |
| Max output | 131.07K | 131.07K |
| Average output | 1.5K tokens | 776 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $1.40 | $0.60Best |
| Output | $4.40 | $1.10Best |
| Cache read | $0.70 | $0.20Best |
| Performance | ||
| Throughput | — | 168.2 tok/s |
| Time to first token | — | 8.5 s |
| Request success (24h) | 66.6% | 99.7%Best |
| Benchmark indexes | ||
| Intelligence Index | 22.4 | 44.8Best |
| Coding Index | 46.5 | 74.8Best |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Structured output | Yes | Yes |
| Reasoning effort | — | low, high, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GLM 5.2 TEE
- GLM 5.3
Intelligence Index
- GLM 5.2 TEE22.4
- GLM 5.344.8
GLM 5.2 TEE: Better than 54% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- GLM 5.2 TEE: 46.5
- GLM 5.3: 74.8Top
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GLM 5.2 TEE: —
- GLM 5.3: 62.2%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GLM 5.2 TEE: —
- GLM 5.3: 29.4%
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- GLM 5.2 TEE: —
- GLM 5.3: 0.3%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GLM 5.2 TEE: —
- GLM 5.3: 1,505 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GLM 5.2 TEE: 1,244 Elo
- GLM 5.3: 1,649 EloTop
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GLM 5.2 TEE: —
- GLM 5.3: 11.2%
AA-LCRv1.1
Reasoning across long documents
- GLM 5.2 TEE: 42.3%
- GLM 5.3: 79.7%Top
MLCR-AA
Long-context reasoning over medical records
- GLM 5.2 TEE: —
- GLM 5.3: 17.2%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM 5.2 TEE: 9.8%
- GLM 5.3: 42.3%Top
GPQA Diamond
Graduate-level science questions
- GLM 5.2 TEE: 68.6%
- GLM 5.3: 91.7%Top
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GLM 5.2 TEE: —
- GLM 5.3: 41.9%
SciCode
Scientific computing in Python
- GLM 5.2 TEE: —
- GLM 5.3: 59.0%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM 5.2 TEE: 42.3%
- GLM 5.3: 79.7%Top
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
- GLM 5.2 TEE
- GLM 5.3
| Leaderboard | GLM 5.2 TEE | GLM 5.3 |
|---|---|---|
| Combined | Not in top 20 | #19 · 5.7% |
Ranks among Noumen catalog models on Combined leaderboards. Only top-20 placements are listed.
- GLM 5.2 TEE
- GLM 5.3
| Leaderboard | GLM 5.2 TEE | GLM 5.3 |
|---|---|---|
| Roleplay | Not in top 20 | #13 · 28.6% |
| Creative writing | Not in top 20 | #9 · 37.0% |
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- GLM 5.2 TEE
- GLM 5.3
| Leaderboard | GLM 5.2 TEE | GLM 5.3 |
|---|---|---|
| Creative Writing v3 | Not in top 20 | #6 · 2077 |
| Longform Writing | Not in top 20 | #11 · 81.8 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
- GLM 5.2 TEE
- GLM 5.3
| Leaderboard | GLM 5.2 TEE | GLM 5.3 |
|---|---|---|
| Mobile Apps | Not in top 20 | #17 · 1192 |
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
- GLM 5.2 TEE
- GLM 5.3
| Leaderboard | GLM 5.2 TEE | GLM 5.3 |
|---|---|---|
| Usage Share | Not in top 20 | #6 · 5.6% |
Ranks among Noumen catalog models on Usage leaderboards. Only top-20 placements are listed.
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.
- Prompt cache hits
- 0.4%
- About $1.40 per 1M input tokens with caching
- Request success (24h)
- 66.6%
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.
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-5.2",
"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-5.2",
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.