GLM 5 Turbo
Z.ai · released Mar 15, 2026
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
Specification
- Context window
- 203K
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
- Uptime
- 100.0%
Intelligence
39.1
87th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
18 t/s
Median across providers
Latency
5.19s
Time to first token
Cost per task
$0.38
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)98.5%
- GPQA Diamond84.7%
- IFBench73.2%
- AA-LCR (long context)66.7%
- SciCode43.6%
- Terminal-Bench Hard33.3%
- Humanity's Last Exam27.8%
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) | 98.5% |
| GPQA Diamond | 84.7% |
| IFBench | 73.2% |
| AA-LCR (long context) | 66.7% |
| SciCode | 43.6% |
| Terminal-Bench Hard | 33.3% |
| Humanity's Last Exam | 27.8% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GPT-5.4 NanoOpenAI39.7
- Qwen3.7 PlusQwen39.4
- GLM 5 TurboZ.ai39.1
- M2.7MiniMax38.9
- Claude Opus 4.6Anthropic38.8
- MiMo-V2.5Xiaomi38.0
- Grok 4.20xAI38.0
- Grok 4.3xAI37.9
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GPT-5.4 Nano | 39.7 |
| Qwen3.7 Plus | 39.4 |
| GLM 5 Turbo | 39.1 |
| M2.7 | 38.9 |
| Claude Opus 4.6 | 38.8 |
| MiMo-V2.5 | 38.0 |
| Grok 4.20 | 38.0 |
| Grok 4.3 | 37.9 |
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
- $1.2
- Output / 1M tokens
- $4
- Cached input / 1M
- $0.24
- Blended 3:1
- $1.9
One task, estimated
$0.38
- 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
- 1,305
- Win rate
- 58.2%
- Strongest at
- 3D scenes
- Tournaments
- 4,053
Elo by category
Dot position on a 1,250–1,325 scale · Elo has no meaningful zero
- 1,305
- 1,298
- 1,297
- 1,293
- 1,290
- 1,254
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 | 1305 | 58.2% |
| UI components | 1298 | 57.2% |
| Game development | 1297 | 57.4% |
| Websites | 1293 | 55.5% |
| Data visualisation | 1290 | 57.3% |
| SVG | 1254 | 57.0% |