- Avg Tokens / Second
- 15.40
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 6690.00
- Runs Analysed
- 6
- Last Updated
- Aug 12, 2026, 07:13 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 130 tok/s (99th percentile) · dashed rule is the model's own mean
Every lane measuring this model
2 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 |
|---|---|---|---|---|---|---|
| deepinfra | via OpenRouter | 15.40 | 2.61 | 29.80 | 6690.00 | 6 |
| deepinfra | direct | 2.51 | 2.51 | 2.51 | 22700.00 | 1 |
Frequently Asked Questions
How fast is gpt-oss-120b?
The latest rolling average throughput is 15.40 tokens per second with an average time to first token of 6690.00 ms across 6 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 12, 2026, 07:13 PM.