Benchmark Overview
78.20
310.00
1244
May 19, 2026, 08:35 AM
Key Insights
llama-3.3-70b streams at 78.20 tokens/second on average across the last 1244 benchmark runs.
Performance fluctuated by 96.20 tokens/second (123.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 310.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 19, 2026, 08:35 AM based on 1244 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-3.3-70b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-3.3-70b | 78.20 | 16.80 | 113.00 | 310.00 |
Frequently Asked Questions
The latest rolling average throughput is 78.20 tokens per second with an average time to first token of 310.00 ms across 1244 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 19, 2026, 08:35 AM.