Qwen 3.8 Max Preview much more token-efficient on input costs
User compares Qwen 3.8 Max Preview against Minimax M3 and 5.6 Sol X/Luna High with identical prompts and system instructions, finding it much more token-efficient on input costs. Follow-up to a prior post mislabeled as Qwen 3.7 Max Preview.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Koharu translates manga pages locally using OCR, inpainting, and LLMs
- Orchestration tool runs AI coding agents in parallel, compares answers
- Real-time Gaussian splats generated on mobile devices
- Newtake AI shows off completely AI-generated rap music video
- ChatGPT Work used to install OpenClaw and Ollama, run local model