Benchmark Overview
40.70
550.00
1420
Mar 26, 2026, 12:32 PM
Key Insights
mistral-large streams at 40.70 tokens/second on average across the last 1420 benchmark runs.
Performance fluctuated by 44.19 tokens/second (108.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 550.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 26, 2026, 12:32 PM based on 1420 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-large
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | mistral-large | 40.70 | 2.31 | 46.50 | 550.00 |
Frequently Asked Questions
The latest rolling average throughput is 40.70 tokens per second with an average time to first token of 550.00 ms across 1420 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 26, 2026, 12:32 PM.