GPT-6 Astra Tops Epoch Capabilities Index Despite Score Revision
GPT-6 Astra tops Epoch AI's Capabilities Index and set a record on the math subindex, but its score was later revised down, with long-horizon software engineering remaining a weakness against Claude Fable 5.1.
2026-09-17 ~ 2026-09-17 · 2 related posts
- GPT-6 Astra's Epoch ECI Score Revised Down on Weak Long-Horizon Software Engineering — Jsevillamol · 2026-09-17
- GPT-6 Astra tops Epoch Capabilities Index but Claude Fable 5.1 still leads software engineering — Jsevillamol · 2026-09-17