GLM 4.7
Z.ai · released Dec 22, 2025
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
Specification
- Context window
- 205K
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- 358.3B
- Licence
- mit
- Serving providers
- 9
- Moderated
- No
- Uptime
- 100.0%
Intelligence
34.5
80th percentile
Coding
45.3
Coding Index
Agentic
26.2
Agentic Index
Output speed
502 t/s
Median across providers
Latency
311ms
Time to first token
Cost per task
$0.16
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)95.9%
- AIME 202595.0%
- LiveCodeBench89.4%
- GPQA Diamond85.9%
- MMLU-Pro85.6%
- AA-LCR (long context)68.0%
- IFBench67.9%
- SciCode45.1%
- Terminal-Bench Hard31.8%
- Humanity's Last Exam27.4%
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) | 95.9% |
| AIME 2025 | 95.0% |
| LiveCodeBench | 89.4% |
| GPQA Diamond | 85.9% |
| MMLU-Pro | 85.6% |
| AA-LCR (long context) | 68.0% |
| IFBench | 67.9% |
| SciCode | 45.1% |
| Terminal-Bench Hard | 31.8% |
| Humanity's Last Exam | 27.4% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GLM 5V TurboZ.ai35.3
- Qwen3.5-27BQwen34.6
- GLM 4.7Z.ai34.5
- M2.5MiniMax34.5
- Hy3 previewTencent34.4
- 34.3
- LongCat 2.0Meituan33.9
- KAT-Coder-Pro V2KwaiPilot33.9
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GLM 5V Turbo | 35.3 |
| Qwen3.5-27B | 34.6 |
| GLM 4.7 | 34.5 |
| M2.5 | 34.5 |
| Hy3 preview | 34.4 |
| Qwen3.5 397B A17B | 34.3 |
| LongCat 2.0 | 33.9 |
| KAT-Coder-Pro V2 | 33.9 |
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
- $0.4
- Output / 1M tokens
- $1.75
- Cached input / 1M
- $0.08
- Blended 3:1
- $0.738
One task, estimated
$0.16
- 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
- 1,248
- Win rate
- 55.3%
- Strongest at
- Websites
- Tournaments
- 30,270
Elo by category
Dot position on a 1,075–1,250 scale · Elo has no meaningful zero
- 1,248
- 1,246
- 1,234
- 1,230
- 1,223
- 1,189
- 1,168
- 1,091
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Websites | 1248 | 55.3% |
| 3D scenes | 1246 | 54.3% |
| UI components | 1234 | 51.0% |
| Game development | 1230 | 55.2% |
| Data visualisation | 1223 | 51.2% |
| SVG | 1189 | 54.3% |
| Mobile apps | 1168 | 49.0% |
| Full-stack apps | 1091 | 44.9% |