Claude Opus 5.5 Tops Epoch Capabilities Index at 167, Edging Out GPT-6 Astra
scaling01 · x · 2026-10-01
Epoch AI's latest Capabilities Index (ECI) puts Claude Opus 5.5 at the top with a score of 167, narrowly ahead of GPT-6 Astra. Claude Sonnet 5.5 scored roughly 165, essentially matching the previous flagship Claude Fable 5.1 — a sign that mid-tier models are closing in on last-generation frontier performance.
More from Models
- Altman: GPT-6.1 Sol was our fastest-growing model ever, slowness under load now fixed — sama · 2026-10-01
- Claude can't write badly: worst output only scores 2/10, and refusal is preemptive — repligate · 2026-10-01
- Open-Source Coding Model IQuest-Q1 Hits Hugging Face, Works with Claude Code — ZabihullahAtal · 2026-10-01
- IQuest-Q1 turns a written brief into a working SaaS dashboard — ZabihullahAtal · 2026-10-01
- PewDiePie gets banned twice by OpenAI for using Sol to distill training data — Hesamation · 2026-10-01
- Cloudflare debuts RL fine-tuning product for Clef, recruiting design partners — michellechen · 2026-10-01