Benchmark Overview
98.90
290.00
1423
Mar 8, 2026, 02:43 AM
Key Insights
llama-3.3-70b streams at 98.90 tokens/second on average across the last 1423 benchmark runs.
Performance fluctuated by 133.19 tokens/second (134.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 290.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 8, 2026, 02:43 AM based on 1423 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 | 98.90 | 3.81 | 137.00 | 290.00 |
Frequently Asked Questions
The latest rolling average throughput is 98.90 tokens per second with an average time to first token of 290.00 ms across 1423 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 8, 2026, 02:43 AM.