Benchmark Overview
64.20
0.27
1168
Dec 26, 2025, 04:25 AM
Key Insights
claude-3-haiku streams at 64.20 tokens/second on average across the last 1168 benchmark runs.
Performance fluctuated by 77.40 tokens/second (120.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.27 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Dec 26, 2025, 04:25 AM based on 1168 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-3-haiku
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | claude-3-haiku | 64.20 | 14.00 | 91.40 | 0.27 |
Frequently Asked Questions
The latest rolling average throughput is 64.20 tokens per second with an average time to first token of 0.27 ms across 1168 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Dec 26, 2025, 04:25 AM.