Benchmark Overview
80.30
200.00
408
May 20, 2026, 10:31 AM
Key Insights
mistral-7b streams at 80.30 tokens/second on average across the last 408 benchmark runs.
Performance fluctuated by 28.90 tokens/second (36.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 200.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 20, 2026, 10:31 AM based on 408 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-7b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | mistral-7b | 80.30 | 57.90 | 86.80 | 200.00 |
Frequently Asked Questions
The latest rolling average throughput is 80.30 tokens per second with an average time to first token of 200.00 ms across 408 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 10:31 AM.