Benchmark Overview
9.10
3150.00
309
May 18, 2026, 05:20 PM
Key Insights
claude-opus-4.1 streams at 9.10 tokens/second on average across the last 309 benchmark runs.
Performance fluctuated by 10.43 tokens/second (114.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 3150.00 ms (high latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 18, 2026, 05:20 PM based on 309 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.
claude-opus-4.1
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | claude-opus-4.1 | 9.10 | 4.87 | 15.30 | 3150.00 |
Frequently Asked Questions
The latest rolling average throughput is 9.10 tokens per second with an average time to first token of 3150.00 ms across 309 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 18, 2026, 05:20 PM.