Reported GPT-6 Astra leads coding index, scores 3% on FrontierMath Erdős

Unconfirmed reports claim GPT-6 'Astra' scores 3% on FrontierMath Erdős while all other tested models score 0%, and leads rival models significantly on a coding agent index.

2026-09-04 ~ 2026-09-05 · 3 related posts

• Astra reportedly leads coding agent index over SOL, Fable, and Spark — XCxBigDong69XCx · 2026-09-04
• GPT-6 Astra scores 3% on FrontierMath Erdős benchmark while every other tested model scores 0% — Every_Foundation5197 · 2026-09-05
• GPT-6 Astra reportedly scores 3% on FrontierMath Erdős, spending $220K in compute — haider1 · 2026-09-05