Benchmark Overview
38.80
0.69
898
Oct 19, 2025, 12:01 AM
Key Insights
deepseek-v3 streams at 38.80 tokens/second on average across the last 898 benchmark runs.
Performance fluctuated by 73.92 tokens/second (190.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.69 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 19, 2025, 12:01 AM based on 898 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-v3
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | deepseek-v3 | 38.80 | 3.68 | 77.60 | 0.69 |
Frequently Asked Questions
The latest rolling average throughput is 38.80 tokens per second with an average time to first token of 0.69 ms across 898 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 19, 2025, 12:01 AM.