Benchmark Overview
26.40
1780.00
226
May 11, 2026, 10:37 AM
Key Insights
claude-4-sonnet streams at 26.40 tokens/second on average across the last 226 benchmark runs.
Performance fluctuated by 24.53 tokens/second (92.9% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1780.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on May 11, 2026, 10:37 AM based on 226 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-4-sonnet
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| anthropic | claude-4-sonnet | 26.40 | 8.37 | 32.90 | 1780.00 |
Frequently Asked Questions
The latest rolling average throughput is 26.40 tokens per second with an average time to first token of 1780.00 ms across 226 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 11, 2026, 10:37 AM.