GLM 5.2 (batch)
Z.ai · released Jun 16, 2026
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Specification
- Context window
- 512K
- Max output
- —
- Knowledge cutoff
- Not stated
- Parameters
- 753.3B
- Licence
- mit
- Serving providers
- 1
- Moderated
- No
Intelligence
52.6
96th percentile
Coding
68.8
Coding Index
Agentic
45.7
Agentic Index
Output speed
115 t/s
Median across providers
Latency
1.06s
Time to first token
Cost per task
$0.21
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)99.1%
- GPQA Diamond89.5%
- AA-LCR (long context)76.7%
- IFBench73.3%
- Terminal-Bench Hard50.8%
- SciCode50.5%
- Humanity's Last Exam41.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 99.1% |
| GPQA Diamond | 89.5% |
| AA-LCR (long context) | 76.7% |
| IFBench | 73.3% |
| Terminal-Bench Hard | 50.8% |
| SciCode | 50.5% |
| Humanity's Last Exam | 41.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Muse Spark 1.1Meta53.2
- GPT-5.4OpenAI53.1
- GLM 5.2 (batch)Z.ai52.6
- GLM 5.2Z.ai52.6
- GPT-5.6 LunaOpenAI52.3
- Gemini 3.5 FlashGoogle52.0
- V4 Flash 0731DeepSeek51.8
- V4 Flash 0423DeepSeek51.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Muse Spark 1.1 | 53.2 |
| GPT-5.4 | 53.1 |
| GLM 5.2 (batch) | 52.6 |
| GLM 5.2 | 52.6 |
| GPT-5.6 Luna | 52.3 |
| Gemini 3.5 Flash | 52.0 |
| V4 Flash 0731 | 51.8 |
| V4 Flash 0423 | 51.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.7
- Output / 1M tokens
- $2.2
- Cached input / 1M
- $0.13
- Blended 3:1
- $1.07
One task, estimated
$0.21
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,363
- Win rate
- 59.7%
- Strongest at
- 3D scenes
- Tournaments
- 2,651
Elo by category
Dot position on a 1,200–1,375 scale · Elo has no meaningful zero
- 1,363
- 1,339
- 1,337
- 1,337
- 1,325
- 1,260
- 1,274
- 1,219
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| 3D scenes | 1363 | 59.7% |
| UI components | 1339 | 58.3% |
| Websites | 1337 | 60.1% |
| Game development | 1337 | 59.1% |
| Data visualisation | 1325 | 57.1% |
| SVG | 1260 | 55.5% |
| Full-stack apps | 1274 | 63.8% |
| Mobile apps | 1219 | 54.0% |