Epoch AI: GPT-6 Astra sets ECI record of 169, tops math and continual learning benchmarks
NathanpmYoung · x · 2026-09-04
Epoch AI, with pre-release access from OpenAI, reports GPT-6 Astra set a new ECI record of 169 (prior best 163), within the reasoning-era trend's uncertainty range. Astra also set records on Epoch's math, continual learning, and game-puzzles benchmarks, and ranks between Opus 4.7 and Fable 5 on the long-horizon coding benchmark MirrorCode.
Related event: GPT-6 Astra Sets ECI Record at 169, Science Benchmark Jumps 42 Points(4 posts)→
More from Models
- UK AISI assessment: Astra reasons in a more compressed style than GPT 5.6 Sol — maksym_andr · 2026-09-04
- Tester: AI-text detector Pangram shows zero false positives, but adversarial rewriting evades it — alex_peys · 2026-09-04
- GPT-6 Astra jumps 42.2pp to top Terminal-Bench-Science at 64.6% — BenBlaiszik · 2026-09-04
- OpenAI researcher teases upcoming model: 'best in class' at computer use, research, coding — athyuttamre · 2026-09-04
- FrontierMath is 'dead' after 664 days as frontier models conquer the math benchmark — willdepue · 2026-09-04
- Matt Shumer's GPT-6 Astra review: Manager Loop sustains a week-long Manhattan build in Unreal — mattshumer_ · 2026-09-04