Benchmark Overview
20.90
1.49
917
Oct 17, 2025, 08:07 AM
Key Insights
claude-4-sonnet streams at 20.90 tokens/second on average across the last 917 benchmark runs.
Performance fluctuated by 30.19 tokens/second (144.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1.49 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 17, 2025, 08:07 AM based on 917 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 | 20.90 | 1.51 | 31.70 | 1.49 |
Frequently Asked Questions
The latest rolling average throughput is 20.90 tokens per second with an average time to first token of 1.49 ms across 917 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 17, 2025, 08:07 AM.