Benchmark Overview
95.80
310.00
1421
Mar 26, 2026, 11:43 PM
Key Insights
llama-3.3-70b streams at 95.80 tokens/second on average across the last 1421 benchmark runs.
Performance fluctuated by 130.19 tokens/second (135.9% 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 Mar 26, 2026, 11:43 PM based on 1421 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 | 95.80 | 3.81 | 134.00 | 310.00 |
Frequently Asked Questions
The latest rolling average throughput is 95.80 tokens per second with an average time to first token of 310.00 ms across 1421 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 26, 2026, 11:43 PM.