OpenAI tackles a batch of hard math problems, outpacing a decade of human progress

bindureddy · x · 2026-10-07

bindureddy reports that OpenAI just released solutions to a set of very hard math problems, claiming the AI solved more problems than humans managed in a decade. He expects AI to soon ace science problems across the board. The post doesn't name the specific benchmark or problem count.

Related event: OpenAI Open-Sources 722 AI-Generated Math Manuscripts, Claiming Progress on Millennium Problems(98 posts)→

Original post →

More from Models

• smallest_ai's Pulse tops Voice Arena diarization + ASR track with 24.4% DER vs 40.7% — rohanpaul_ai · 2026-10-07
• unsloth's EmbeddingGemma-2 GGUF quantization trends on Hugging Face — unsloth · 2026-10-07
• Pro users baffled as Deep Research is chat-only while Astra is work-only — eigenron · 2026-10-07
• AI Research Agents Have Radically Different Styles—Leaderboards Reduce Them to One Blind Number — ChengleiSi · 2026-10-07
• Dev: Claude wins benchmarks but Codex better at doing what I want — Kuprel · 2026-10-07
• DataCamp founder slams OpenAI Codex's 'insane' automatic resets — hugobowne · 2026-10-07

Models channel →