Benchmark Overview
29.00
1390.00
113
Jan 24, 2026, 03:03 AM
Key Insights
deepseek-v3 streams at 29.00 tokens/second on average across the last 113 benchmark runs.
Performance fluctuated by 65.03 tokens/second (224.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1390.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Jan 24, 2026, 03:03 AM based on 113 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 | 29.00 | 1.17 | 66.20 | 1390.00 |
Frequently Asked Questions
The latest rolling average throughput is 29.00 tokens per second with an average time to first token of 1390.00 ms across 113 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jan 24, 2026, 03:03 AM.