Benchmark Overview
180.00
1320.00
115
Mar 13, 2026, 12:00 PM
Key Insights
gpt-oss-120b streams at 180.00 tokens/second on average across the last 115 benchmark runs.
Performance fluctuated by 378.49 tokens/second (210.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1320.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 13, 2026, 12:00 PM based on 115 total samples.
Performance Distribution
Distribution of throughput measurements showing performance consistency across benchmark runs.
Performance Over Time
Historical performance trends showing how throughput has changed over the benchmarking period.
gpt-oss-120b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cerebras | gpt-oss-120b | 180.00 | 1.51 | 380.00 | 1320.00 |
Frequently Asked Questions
The latest rolling average throughput is 180.00 tokens per second with an average time to first token of 1320.00 ms across 115 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 13, 2026, 12:00 PM.