llm-benchmarks
githubdrose.io

Qwen3.5 Plus 2026-04-20 Benchmarks


Measured on alibaba

5 runs
Avg Tokens / Second
1.96
Avg Time to First Token (ms)
32100.00
Runs Analysed
5
Last Updated
Sep 1, 2026, 04:07 AM

Throughput distribution

Throughput over time

Qwen3.5 Plus 2026-04-20alibaba1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 55 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
alibabaQwen3.5 Plus 2026-04-201.941.862.0032700.00
alibabaQwen3.5 Plus 2026-04-201.991.991.9931500.00

Frequently Asked Questions

How fast is Qwen3.5 Plus 2026-04-20?
The latest rolling average throughput is 1.96 tokens per second with an average time to first token of 32100.00 ms across 5 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 04:07 AM.

Related models