Will any AI model reach ___ Math Arena Score by December 31?

Traders currently price "1525" at 100% for "Will any AI model reach ___ Math Arena Score by December 31?". Over the past 24 hours that probability moved up 3.6 points. Full distribution: 1525 100%, 1550 100%, 1575 85%, 1600 36%. The market has traded $112K in total volume and resolves Dec 31, 2026. Recent progress on MathArena benchmarks shows frontier models rapidly advancing mathematical reasoning, with Anthropic's Claude Opus 5 (max) leading at 84.4% overall and OpenAI's GPT-5.6 and GPT-5.5 variants close behind. Claude and GPT-5 series have dominated recent competitions, including near-saturation on USAMO 2026 at 95%, while open models like Moonshot's Kimi trail. Labs continue releasing enhanced reasoning variants and post-training datasets targeting research-level problems. Key swing factors include new competition releases through year-end, additional model launches or fine-tunes, and whether harder ArXivMath or FrontierMath-style problems maintain headroom before December 31. Trader sentiment reflects the pace of iterative gains against an evolving, contamination-resistant leaderboard.

Odds sourced live from Polymarket, refreshed through the day. Prediction-market participation carries risk and may be restricted in your jurisdiction. Informational only — not investment advice.