Polymarket Opens Betting on OpenAI's 'Astra' Model for Humanity's Last Exam
Polymarket · x · 2026-08-14
Polymarket has launched a prediction market for OpenAI's upcoming 'Astra' model, focusing on its performance on the Humanity's Last Exam (HLE) benchmark.
The market will resolve based on the official HLE accuracy displayed on agi.safe.ai. Currently, the market predicts a 77% chance that the model will achieve an accuracy of 40% or higher.
More from Models
- User tests Gemini on game guide, finds frequent errors, says AI still in infancy — JaxUK89 · 2026-08-14
- Apple reportedly built its own China AI model with Alibaba in rare cross-border deal — The Verge AI · 2026-08-14
- Gemini 3.7 Flash Rolling Out to Web and Mobile Users — testingcatalog · 2026-08-14
- MiniMax H3 open weights limited to 768P, 2K path requires API — ImmediateGas8328 · 2026-08-14
- GLM-5.3 excels at 3D game dev with improved spatial capabilities — cedric_chee · 2026-08-14
- User Switches Back to ChatGPT for SVG Conversion, Finds Claude Code Better — MS_Fume · 2026-08-14