Benchmark Overview
64.50
570.00
238
Apr 3, 2026, 12:05 PM
Key Insights
deepseek-r1 streams at 64.50 tokens/second on average across the last 238 benchmark runs.
Performance fluctuated by 107.44 tokens/second (166.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 570.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Apr 3, 2026, 12:05 PM based on 238 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.
deepseek-r1
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | deepseek-r1 | 64.50 | 5.56 | 113.00 | 570.00 |
Frequently Asked Questions
The latest rolling average throughput is 64.50 tokens per second with an average time to first token of 570.00 ms across 238 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Apr 3, 2026, 12:05 PM.