Which tier did best in Benchmark 2?

It depends on what you value:

• Honesty: Heavy 22/22, Max 21/22, Flash 20/22.
• Purity: Max and Heavy 20/20, Flash 19/20.
• Coding (combined): essentially tied: Flash 93.9%, Max and Heavy 93.8%.
• Speed and cost: Flash clearly best: 3.5 s and $1.64 per 1,000 tasks vs Heavy's 8.7 s and $3.64.

With samples this small, the main message is that all three are strong; pick by speed and cost, and use Heavy where honesty under hard pressure matters most.

Good to know#

• Not sure which tier? auto lets the product choose per step. What auto does
• Every tier shares the same 1M-token context window (1,048,576 tokens). Context window
• Line Code was retired on Nov 1, 2026; its ids answer 410 model_retired. Line Code retirement

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.