Measured on z-ai
4 runs- Avg Tokens / Second
- 3.17
- Avg Time to First Token (ms)
- 21600.00
- Runs Analysed
- 4
- Last Updated
- Sep 1, 2026, 04:27 AM
Throughput distribution
Throughput over time
Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 45 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it
Every provider serving this model
1 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| z-ai | GLM 5V Turbo | 3.17 | 2.12 | 4.77 | 21600.00 |
Frequently Asked Questions
How fast is GLM 5V Turbo?
The latest rolling average throughput is 3.17 tokens per second with an average time to first token of 21600.00 ms across 4 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 04:27 AM.