GPT-6 Astra (max) reportedly hits 51% pass@5 on ZeroBench, far above 30% SOTA
scaling01 · x · 2026-09-24
Blogger JRobertsAI shared (unverified) claimed scores of GPT-6 Astra (max) on the ZeroBench visual reasoning benchmark: pass@5 of 51% versus a previous SOTA of 30%, and pass^5 of 35% versus a previous SOTA of just 13%.
If genuine, the jump suggests major gains in both visual reasoning performance and sampling consistency.
Related event: GPT-6 Astra Reportedly Tops ZeroBench, Beating Human Baselines(2 posts)→
More from Models
- ChatGPT Voice with tools and MCP impresses: interruptible, pulls local Mac files — athyuttamre · 2026-09-24
- Not every job needs the smartest AI model—good enough wins — ChrisUniverse · 2026-09-24
- Flash 3.8 impresses as a rapid prototyper: turning a button component into a puppy with one prompt — BuffaloConscious7919 · 2026-09-24
- TeleOCR, a Qwen2.5-VL-based document parsing model, trends on Hugging Face — StarDoc-AI · 2026-09-24
- Rumor: SSI to launch its first model this month after security-related delay — iruletheworldmo · 2026-09-24
- Which sub-40B finetunes work best for mimicking a writing style? — Borkato · 2026-09-24