Benchmark Overview
22.80
1010.00
239
Mar 27, 2026, 06:00 AM
Key Insights
llama-3.1-405b streams at 22.80 tokens/second on average across the last 239 benchmark runs.
Performance fluctuated by 37.45 tokens/second (164.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1010.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 27, 2026, 06:00 AM based on 239 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 | 22.80 | 1.35 | 38.80 | 1010.00 |
Frequently Asked Questions
The latest rolling average throughput is 22.80 tokens per second with an average time to first token of 1010.00 ms across 239 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 27, 2026, 06:00 AM.