Epoch AI: GPT-6.2 Astra scores 174 on ECI, matching Fable 5.2
scaling01 · x · 2026-11-18
Epoch AI's independent evaluation gives GPT-6.2 Astra a score of 174 on the Epoch Capabilities Index (ECI), on par with Fable 5.2 and above what the pre-Astra reasoning-era trend would have predicted. The chart puts the reasoning-era frontier trend at +16 ECI/year (90% CI: 14–18), with Astra at the upper edge of the prediction band. Scores are based on Epoch's own benchmarks run before launch and will be updated as more results come in.
More from Models
- OpenAI drops GPT-6.2 Astra and GPT-6.2 Sol — danshipper · 2026-11-18
- OpenAI ships GPT-6.2 Astra and GPT-6.2 Sol — danshipper · 2026-11-18
- Early GPT-6.2 reviews split: Matt Shumer calls Astra/Sol essentially unusable — Independent-Wind4462 · 2026-11-18
- Microsoft's MAI Models Go Live on Copilot, OpenRouter and Vercel — marlene_zw · 2026-11-18
- Theo's Long Critique: GPT-6.2 Astra Is Painful to Use, Opus 5.5 Still Better Overall — Angaisb_ · 2026-11-18
- Microsoft announces MAI Decision 1, Code 2, Realtime 1 and more at Ignite — testingcatalog · 2026-11-18