Benchmark Overview
56.60
210.00
416
May 20, 2026, 02:07 PM
Key Insights
mistral-small streams at 56.60 tokens/second on average across the last 416 benchmark runs.
Performance fluctuated by 16.30 tokens/second (28.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 210.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 02:07 PM based on 416 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.
mistral-small
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | mistral-small | 56.60 | 43.10 | 59.40 | 210.00 |
Frequently Asked Questions
The latest rolling average throughput is 56.60 tokens per second with an average time to first token of 210.00 ms across 416 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 02:07 PM.