Qwen3.6 35B A3B vs Qwen3.8 Max (0902): accuracy, speed and price

• Qwen3.8 Max (0902) is more accurate: 75.0% against 37.5% on the same 80 questions, a 37.5-point gap that is statistically significant.
• Qwen3.6 35B A3B is 3.0× cheaper per question as billed ($0.0037 vs $0.011), reasoning tokens included.
• Qwen3.6 35B A3B generates text 2.9× faster: 135 tokens per second against 46.
• Qwen3.6 35B A3B starts answering sooner: 0.4 s to the first token, against 1.2 s for Qwen3.8 Max (0902).
• Qwen3.8 Max (0902) accepts more context: 1M tokens against 262k.

Which should you choose?

Choose Qwen3.6 35B A3B for the lower cost per correct answer ($0.0099 against $0.015), faster streaming, a quicker first token, open weights you can run yourself and more hosts to choose from on OpenRouter (10 against 1). Choose Qwen3.8 Max (0902) for the most accurate answers of the two, shorter outputs (about 1,722 tokens per question against 3,563) and a 1M-token context window. The widest subject gap is in science: Qwen3.8 Max (0902) answered 24 of 30 correctly, Qwen3.6 35B A3B 9 of 30. With so few questions per subject, treat this as a lead to test on your own prompts, not a result.

Accuracy gap -37.5 points (z = -4.78). We call a winner only when z is at least 1.96, the usual 95% threshold. Speed, latency and price need a 10% margin.