Qwen4 Max Preview appears sans benchmarks, rumors call it disappointing
kimmonismus · x · 2026-11-11
LuminaBench spotted Qwen4 Max Preview quietly going live — with no benchmarks attached. kimmonismus relays rumors that Qwen 4 is disappointing, attributing the slowdown to Alibaba clamping down to prevent distillation of Anthropic's models; if true, he argues, US labs remain far ahead. Unverified for now.
More from Models
- teortaxesTex: RL may give coding models 'full fluency' with no superhuman headroom — teortaxesTex · 2026-11-11
- SenseNova 6.8 Flash Targets Agent Continuity, Outputs Editable Blender Scenes — JaynitMakwana · 2026-11-11
- Matthew Berman news roundup: NVIDIA CEO affair, Claude Fable 5.2, Gemini 4 Carbon, 12+ model releases — Matthew Berman · 2026-11-11
- Dev claims ~700 tokens/s running Qwen 3 27B on a single RTX 5090 — IgorCarron · 2026-11-11
- Inkling 2 Small goes free on OpenCode: 594B MoE, 1M context, multimodal — ZhongRuiqi · 2026-11-11
- Gemini free tier users report usage limit quietly nerfed from ~2% to 6% per prompt — ItsMichaelRay · 2026-11-11