Benchmark Overview
15.70
0.00
8
May 28, 2026, 08:37 AM
Key Insights
Qwen3-Coder-480B-A35B-Instruct-Turbo streams at 15.70 tokens/second on average across the last 8 benchmark runs.
Performance fluctuated by 20.82 tokens/second (132.6% coefficient of variation), indicating variable behavior across benchmark runs.
Latest measurements completed on May 28, 2026, 08:37 AM based on 8 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.
Qwen3-Coder-480B-A35B-Instruct-Turbo
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| deepinfra | Qwen3-Coder-480B-A35B-Instruct-Turbo | 15.70 | 4.28 | 25.10 | 0.00 |
Frequently Asked Questions
The latest rolling average throughput is 15.70 tokens per second with an average time to first token of 0.00 ms across 8 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 28, 2026, 08:37 AM.