Benchmark Overview
15.50
1090.00
224
May 11, 2026, 03:18 PM
Key Insights
llama-3.1-405b streams at 15.50 tokens/second on average across the last 224 benchmark runs.
Performance fluctuated by 18.44 tokens/second (119.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1090.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 11, 2026, 03:18 PM based on 224 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-3.1-405b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| deepinfra | llama-3.1-405b | 15.50 | 4.36 | 22.80 | 1090.00 |
Frequently Asked Questions
The latest rolling average throughput is 15.50 tokens per second with an average time to first token of 1090.00 ms across 224 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 11, 2026, 03:18 PM.