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.
More from coding & agent
- Anyone's agents actually making money? A dev's reality check on x402 agent payments — thranduilsson · 2026-09-21
- Tsinghua's DiffuTester generates unit tests with diffusion LLMs 2-3x faster — jiqizhixin · 2026-09-21
- Turning a Linux desktop into an agent workspace: Claude, Codex and Hermes on Omarchy — Teknium · 2026-09-21
- Developer builds jev, an interpreter that reasons over plain-English facts and rules, inspired by Geoffrey Litt — narphorium · 2026-09-21
- evmscope MCP server ships 20 blockchain tools for AI agents across 5 EVM chains — modelcontextprotocol · 2026-09-21
- The Latent Space adds agent registry, Elo duels and x402 credit economy — modelcontextprotocol · 2026-09-21