Qwen 3.8 Max Scores 96.1% on Tīrtha Tool-Calling Bench at a Quarter of Opus 5.5's Cost

Key Info

TirthaAI published a Tīrtha Bench review of Qwen 3.8 Max, run with free credits from GMI Cloud, and found it strong enough to move Tīrtha's top tier onto the model.

Highlights

• With reasoning turned off, Qwen 3.8 Max scored 96.1% across 800 tool-calling tasks.
• It passed 100 of 100 trick requests, putting it level with Opus 5.5 at roughly a quarter of the cost per correct answer.
• Under load, 99% of tool calls returned within 4 seconds, with zero errors across 1,840 calls.
• TirthaAI says it is moving Tīrtha's top level to Qwen 3.8 Max as a result.