Z.ai · Open weights
GLM 5.3
GLM-5.3 for long-horizon autonomous coding and engineering workflows. This variant defaults to the model's low reasoning tier for faster responses.
- Reasoning
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Reasoning effort
- low · high · max
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.60
- Output
- $1.10
- Cache read
- $0.20
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 131.1K
- Average output (7 days)
- 776 tokens
- Longer than 64% of 468 models
Side by side
GLM 5.3 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM 5.3Z.aiThis model | GLM 5.2Z.aiRemove | |
|---|---|---|
| Provider | Z.ai | Z.ai |
| Discovery tier | Open weights | Open weights |
| Added | Aug 14, 2026 | Jun 15, 2026 |
| Limits | ||
| Context window | 1.05M | 1.05M |
| Max output | 131.07K | 131.07K |
| Average output | 776 tokens | 839 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.60 | $0.42Best |
| Output | $1.10Best | $1.32 |
| Cache read | $0.20 | $0.078Best |
| Performance | ||
| Throughput | 168.2 tok/sBest | 96.8 tok/s |
| Time to first token | 8.5 s | 1.6 sBest |
| Request success (24h) | 99.7%Best | 99.6% |
| Benchmark indexes | ||
| Intelligence Index | 44.8Best | 22.4 |
| Coding Index | 74.8Best | 46.5 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Structured output | Yes | Yes |
| Reasoning effort | low, high, max | none, high, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GLM 5.3
- GLM 5.2
Intelligence Index
- GLM 5.344.8
- GLM 5.222.4
GLM 5.3 tested at max reasoning effort
GLM 5.3: Better than 90% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- GLM 5.3: 74.8Top
- GLM 5.2: 46.5
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GLM 5.3: 62.2%
- GLM 5.2: —
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GLM 5.3: 29.4%
- GLM 5.2: —
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- GLM 5.3: 0.3%
- GLM 5.2: —
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GLM 5.3: 1,505 Elo
- GLM 5.2: —
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GLM 5.3: 1,649 EloTop
- GLM 5.2: 1,244 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GLM 5.3: 11.2%
- GLM 5.2: —
AA-LCRv1.1
Reasoning across long documents
- GLM 5.3: 79.7%Top
- GLM 5.2: 42.3%
MLCR-AA
Long-context reasoning over medical records
- GLM 5.3: 17.2%
- GLM 5.2: —
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM 5.3: 42.3%Top
- GLM 5.2: 9.8%
GPQA Diamond
Graduate-level science questions
- GLM 5.3: 91.7%Top
- GLM 5.2: 68.6%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GLM 5.3: 41.9%
- GLM 5.2: —
SciCode
Scientific computing in Python
- GLM 5.3: 59.0%
- GLM 5.2: —
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM 5.3: 79.7%Top
- GLM 5.2: 42.3%
Scores from Artificial Analysis, updated Oct 26, 2026. GLM 5.3 was tested at max reasoning effort; compare scores measured at the same effort.Artificial Analysis
- GLM 5.3
- GLM 5.2
| Leaderboard | GLM 5.3 | GLM 5.2 |
|---|---|---|
| Combined | #19 · 5.7% | Not in top 20 |
Ranks among Noumen catalog models on Combined leaderboards. Only top-20 placements are listed.
- GLM 5.3
- GLM 5.2
| Leaderboard | GLM 5.3 | GLM 5.2 |
|---|---|---|
| Roleplay | #13 · 28.6% | Not in top 20 |
| Creative writing | #9 · 37.0% | Not in top 20 |
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- GLM 5.3
- GLM 5.2
| Leaderboard | GLM 5.3 | GLM 5.2 |
|---|---|---|
| Creative Writing v3 | #6 · 2077 | Not in top 20 |
| Longform Writing | #11 · 81.8 | Not in top 20 |
| EQ-Bench 4 | Not in top 20 | #17 · 1211 |
| EQ-Bench 3 | Not in top 20 | #6 · 1563 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
- GLM 5.3
- GLM 5.2
| Leaderboard | GLM 5.3 | GLM 5.2 |
|---|---|---|
| Mobile Apps | #17 · 1192 | Not in top 20 |
| UI Component | Not in top 20 | #20 · 1291 |
| Data Visualization | Not in top 20 | #19 · 1285 |
| Agentic Game Dev | Not in top 20 | #8 · 1170 |
| Web Apps | Not in top 20 | #15 · 1223 |
| Full Stack | Not in top 20 | #11 · 1241 |
| Native Apps | Not in top 20 | #14 · 1181 |
Ranks among Noumen catalog models on Design Arena leaderboards. Only top-20 placements are listed.Design Arena
- GLM 5.3
- GLM 5.2
| Leaderboard | GLM 5.3 | GLM 5.2 |
|---|---|---|
| Usage Share | #6 · 5.6% | Not in top 20 |
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.
- Throughput
- 168.2 tok/s
- Faster than 78% of 254 models
- Time to first token
- 8.5 s
- Quicker than 16% of 254 models
- Prompt cache hits
- 61.1%
- About $0.36 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": "z-ai/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="z-ai/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.