Benchmark Overview
104.00
300.00
1399
Jun 25, 2026, 03:12 AM
Key Insights
llama-4-maverick streams at 104.00 tokens/second on average across the last 1399 benchmark runs.
Performance fluctuated by 107.10 tokens/second (103.0% 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 Jun 25, 2026, 03:12 AM based on 1399 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 | 104.00 | 28.90 | 136.00 | 300.00 |
Frequently Asked Questions
The latest rolling average throughput is 104.00 tokens per second with an average time to first token of 300.00 ms across 1399 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 25, 2026, 03:12 AM.