Benchmark Overview
107.00
320.00
1242
May 20, 2026, 09:29 AM
Key Insights
llama-4-maverick streams at 107.00 tokens/second on average across the last 1242 benchmark runs.
Performance fluctuated by 87.30 tokens/second (81.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 320.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 09:29 AM based on 1242 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-maverick
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-4-maverick | 107.00 | 46.70 | 134.00 | 320.00 |
Frequently Asked Questions
The latest rolling average throughput is 107.00 tokens per second with an average time to first token of 320.00 ms across 1242 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 09:29 AM.