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
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
- ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12
- LMArena Launches Agent Arena for Head-to-Head Agent Evaluation — arena · 2026-11-12
- LLMs lack hyperlocal municipal data, explains disputed Texas power outage debate — csuwildcat · 2026-11-12
- Claude API's per-message effort lets you switch reasoning levels without breaking prompt cache — lyraxana · 2026-11-12