Benchmark Overview
35.10
0.33
893
Dec 24, 2025, 05:21 AM
Key Insights
llama-3.1-nemotron-ultra streams at 35.10 tokens/second on average across the last 893 benchmark runs.
Performance fluctuated by 29.41 tokens/second (83.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.33 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Dec 24, 2025, 05:21 AM based on 893 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.
llama-3.1-nemotron-ultra
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openrouter | llama-3.1-nemotron-ultra | 35.10 | 8.69 | 38.10 | 0.33 |
Frequently Asked Questions
The latest rolling average throughput is 35.10 tokens per second with an average time to first token of 0.33 ms across 893 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Dec 24, 2025, 05:21 AM.