Measured on coreweave
2 runs- Avg Tokens / Second
- 9.20
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 6560.00
- Runs Analysed
- 2
- Last Updated
- Oct 10, 2026, 06:43 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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 46 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples
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 |
|---|---|---|---|---|---|---|
| coreweave | via OpenRouter | 9.20 | 5.48 | 12.90 | 6560.00 | 2 |
| coreweave | direct | 8.28 | 6.46 | 11.10 | 6290.00 | 5 |
Frequently Asked Questions
How fast is gpt-oss-120b?
The latest rolling average throughput is 9.20 tokens per second with an average time to first token of 6560.00 ms across 2 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 10, 2026, 06:43 AM.