OpenAI released GPT-6.1 Sol on September 29, 2026, just days after GPT-6 Sol, positioning the Sol line as the company's latest efficient flagship variant priced at $2/$10 per million tokens. Humanity's Last Exam remains a demanding 2,500-question expert-level benchmark across dozens of subjects, where current top scores sit in the low-to-mid 60s on tool-augmented or verified runs, led by Anthropic's Claude Opus 5.5 and Fable 5.1. GPT-6.1 Sol already appears on Artificial Analysis HLE evaluations at 52.9%, trailing leaders but showing incremental gains over prior GPT-5.6 Sol results. Traders are watching for official OpenAI benchmark disclosures, any Sol-specific HLE leaderboard entries, and potential competitive responses from Google or Anthropic ahead of year-end model updates.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedView resolved

Beware of external links.
Beware of external links.
Frequently Asked Questions