Qwen3.6 Plus tokens per second

Live benchmark data for Qwen3.6 Plus on opencode-go-anthropic. Speed, latency, and reliability — benchmarked every ~10 minutes.

Latest TPS
55.6 tok/s
24h avg TPS
55.6 tok/s
TTFT
1.0s
24h reliability
17%
Last tested
40m ago

Tokens per second over time

Time to first token over time

Speed is measured as output tokens ÷ generation time. Each benchmark fires one streaming chat completion with a fixed ~300-token prompt, every ~10 minutes. Full methodology →