Benchmark Overview
164.00
790.00
192
Feb 4, 2026, 12:00 AM
Key Insights
qwen-3-235b-instruct streams at 164.00 tokens/second on average across the last 192 benchmark runs.
Performance fluctuated by 261.26 tokens/second (159.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 790.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 4, 2026, 12:00 AM based on 192 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.
qwen-3-235b-instruct
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cerebras | qwen-3-235b-instruct | 164.00 | 2.74 | 264.00 | 790.00 |
Frequently Asked Questions
The latest rolling average throughput is 164.00 tokens per second with an average time to first token of 790.00 ms across 192 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 4, 2026, 12:00 AM.