WHAT NEW IN X11.03 TUE

AI collections from X · 22 collections · 66,612 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 1 hour ago
gpt-6THREAD

Epoch AI: GPT-6 Astra tops ECI capability index

Astra sets new records on the Epoch Capabilities Index and its math component, ahead of Claude Fable 5.1, though Fable 5.1 remains state-of-the-art on software engineering benchmarks.

Epoch AI
@EpochAIResearchArchived 2026.09.17Originally posted 2026.09.17
THREADPosted in 2 parts

  1. GPT-6 Astra leads the Epoch Capabilities Index (ECI), ahead of competing models like Claude Fable 5.1, and its Math-ECI also sets a new record. However, on software engineering benchmarks, Fable 5.1 remains state-of-the-art.

    Epoch AI: GPT-6 Astra tops ECI capability index (thread part 1)

  2. Based on pre-release evals, we gave GPT-6 Astra an overall ECI of 169 at launch. Only one of its benchmark results at the time was in software engineering (MirrorCode). But since then, three more SWE results have since been added, and its ECI has subsequently fallen to 166.

Epoch AI @EpochAIResearchOriginally posted 2026.09.17
Open original on X
x.com/epochairesearch/status/2100279761339887847Archived 2026.09.17 10:17
Open original on X