Benchmark Overview
24.70
610.00
383
May 19, 2026, 09:04 PM
Key Insights
llama-3.1-70b streams at 24.70 tokens/second on average across the last 383 benchmark runs.
Performance fluctuated by 5.00 tokens/second (20.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 610.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 19, 2026, 09:04 PM based on 383 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-3.1-70b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-3.1-70b | 24.70 | 20.80 | 25.80 | 610.00 |
Frequently Asked Questions
The latest rolling average throughput is 24.70 tokens per second with an average time to first token of 610.00 ms across 383 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 19, 2026, 09:04 PM.