llm-benchmarks
githubdrose.io

gpt-oss-120b Benchmarks


Measured on venice

3 runs
Avg Tokens / Second
10.50
Decode Tokens / Second
—
Avg Time to First Token (ms)
5550.00
Runs Analysed
3
Last Updated
Nov 7, 2026, 05:22 AM

Throughput distribution

Throughput over time

gpt-oss-120bvenice41tok/s

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 53 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
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
venicevia OpenRouter10.505.8813.505550.003
venicedirect6.402.2410.6013100.002

Frequently Asked Questions

How fast is gpt-oss-120b?
The latest rolling average throughput is 10.50 tokens per second with an average time to first token of 5550.00 ms across 3 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 7, 2026, 05:22 AM.

Related models