GPT-6 Pro Best Ever for Math/ML but Trails Astra Max; Tester Runs Pro+5.1+Max Ensemble

MParakhin · x · 2026-09-21

After more testing, MParakhin reports GPT-6 Pro is the best model ever for Math/ML/Brainstorming, though less decisively this time: OpenAI appears to run agents at High effort (maybe xHigh), making Pro reliable but occasionally losing to Astra Max.

For the toughest problems, his workflow runs Pro, 5.1, and Max separately, then pastes everything into Max for final aggregation.

Original post →

More from coding & agent

coding & agent channel →