- Avg Tokens / Second
- 3.75
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 77400.00
- Runs Analysed
- 7
- Last Updated
- Sep 17, 2026, 02:45 PM
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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 10 tok/s (99th percentile) · dashed rule is the model's own mean
Every lane measuring this model
1 measured · live first · a lane is a provider, a catalogue id and a transport| Provider | Lane | Avg Toks/Sec | Min | Max | Avg TTF (ms) | n |
|---|---|---|---|---|---|---|
| openai | direct | 3.75 | 2.51 | 5.55 | 77400.00 | 7 |
Frequently Asked Questions
How fast is GPT-5.4-pro?
The latest rolling average throughput is 3.75 tokens per second with an average time to first token of 77400.00 ms across 7 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 17, 2026, 02:45 PM.