DeepSeek's New Models Burn Through 'Thinking Tokens' During Testing
SimplyAnnisa · x · 2026-08-24
Users report that DeepSeek's new models (codenamed Melon and Marshmallow) repeatedly hit max-token limits on identical problems, suggesting they are burning through 'thinking tokens' excessively. This is seen as a comparison of different training approaches, with the final version depending on which survives real-world testing.
More from Models
- OpenAI ships GPT-Live-1.1: new voices in six languages, fewer confirmations — OpenAI · 2026-10-16
- Muse Spark model appears on LMArena, testable in Battle and Agent modes — arena · 2026-10-16
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Ilya Sutskever questions Meta license clause taxing MaaS providers above $20M revenue — ilyasu · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- Midas flags inconsistent Claude limits: 33% weekly and 45% window usage despite $100 credits, yet out of API credits — TheMoonMidas · 2026-10-16