Benchmark Overview
76.60
310.00
1272
May 7, 2026, 11:44 PM
Key Insights
llama-3.3-70b streams at 76.60 tokens/second on average across the last 1272 benchmark runs.
Performance fluctuated by 61.30 tokens/second (80.0% 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 7, 2026, 11:44 PM based on 1272 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 | 76.60 | 38.00 | 99.30 | 310.00 |
Frequently Asked Questions
The latest rolling average throughput is 76.60 tokens per second with an average time to first token of 310.00 ms across 1272 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 7, 2026, 11:44 PM.