Benchmark Overview
105.00
0.26
81
Oct 28, 2025, 10:43 AM
Key Insights
llama-4-scout streams at 105.00 tokens/second on average across the last 81 benchmark runs.
Performance fluctuated by 53.40 tokens/second (50.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.26 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 28, 2025, 10:43 AM based on 81 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-4-scout
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-4-scout | 105.00 | 72.60 | 126.00 | 0.26 |
Frequently Asked Questions
The latest rolling average throughput is 105.00 tokens per second with an average time to first token of 0.26 ms across 81 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 28, 2025, 10:43 AM.