GLM 4.7 Flash
Z.ai · released Jan 19, 2026
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
Specification
- Context window
- 200K
- Max output
- 118K
- Knowledge cutoff
- Not stated
- Parameters
- 31.2B
- Licence
- mit
- Serving providers
- 3
- Moderated
- No
- Uptime
- 100.0%
Intelligence
14.9
57th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
48 t/s
Median across providers
Latency
327ms
Time to first token
Cost per task
$0.04
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)98.8%
- IFBench60.8%
- GPQA Diamond58.1%
- AA-LCR (long context)41.7%
- Terminal-Bench Hard22.0%
- Humanity's Last Exam7.6%
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) | 98.8% |
| IFBench | 60.8% |
| GPQA Diamond | 58.1% |
| AA-LCR (long context) | 41.7% |
| Terminal-Bench Hard | 22.0% |
| Humanity's Last Exam | 7.6% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Gemini 3.1 Flash LiteGoogle15.6
- 15.6
- Claude Haiku 4.5Anthropic15.4
- Kimi K2 0905Moonshot AI15.3
- gpt-oss-20b (free)OpenAI15.2
- o1OpenAI15.2
- GLM 4.7 FlashZ.ai14.9
- GLM 4.6Z.ai14.9
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Gemini 3.1 Flash Lite | 15.6 |
| Gemini 3.1 Flash Lite Preview | 15.6 |
| Claude Haiku 4.5 | 15.4 |
| Kimi K2 0905 | 15.3 |
| gpt-oss-20b (free) | 15.2 |
| o1 | 15.2 |
| GLM 4.7 Flash | 14.9 |
| GLM 4.6 | 14.9 |
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
- $0.06
- Output / 1M tokens
- $0.4
- Cached input / 1M
- Not offered
- Blended 3:1
- $0.145
One task, estimated
$0.04
- 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
- 1,209
- Win rate
- 57.6%
- Strongest at
- UI components
- Tournaments
- 583
Elo by category
Dot position on a 1,025–1,225 scale · Elo has no meaningful zero
- 1,209
- 1,196
- 1,138
- 1,124
- 1,121
- 1,036
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1209 | 57.6% |
| Websites | 1196 | 54.0% |
| Game development | 1138 | 49.7% |
| Data visualisation | 1124 | 45.3% |
| 3D scenes | 1121 | 51.2% |
| SVG | 1036 | 44.2% |