Benchmark Overview
99.20
300.00
1422
Mar 26, 2026, 10:42 PM
Key Insights
llama-4-scout streams at 99.20 tokens/second on average across the last 1422 benchmark runs.
Performance fluctuated by 126.67 tokens/second (127.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 300.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 26, 2026, 10:42 PM based on 1422 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 | 99.20 | 3.33 | 130.00 | 300.00 |
Frequently Asked Questions
The latest rolling average throughput is 99.20 tokens per second with an average time to first token of 300.00 ms across 1422 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 26, 2026, 10:42 PM.