Benchmark Overview
61.50
590.00
217
Mar 8, 2026, 06:00 AM
Key Insights
devstral-small streams at 61.50 tokens/second on average across the last 217 benchmark runs.
Performance fluctuated by 128.76 tokens/second (209.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 590.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 8, 2026, 06:00 AM based on 217 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.
devstral-small
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| deepinfra | devstral-small | 61.50 | 9.24 | 138.00 | 590.00 |
Frequently Asked Questions
The latest rolling average throughput is 61.50 tokens per second with an average time to first token of 590.00 ms across 217 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 8, 2026, 06:00 AM.