Will any AI model reach a Chatbot Arena score of at least 1550 by December 31?
As of September 5, 2026, the market gives “Will any AI model reach a Chatbot Arena score of at least 1550 by December 31?” a 81% chance of NO.
| YES odds | 19% |
|---|---|
| NO odds | 81% |
| Volume | $51,772 |
| Closes | January 1, 2027 |
Updated September 5, 2026 · Live data from Polymarket
About this market
Recent releases from OpenAI's GPT-6 Astra and Anthropic's Claude Fable 5.1 and Mythos 5.1 in early September 2026 highlight accelerating frontier progress, with these models posting gains on agentic benchmarks like Terminal-Bench and ARC-AGI that often correlate with Chatbot Arena or Text Arena Elo lifts. Anthropic variants currently lead overall leaderboards near 1505-1508 Elo, but OpenAI and Google DeepMind updates, including Gemini 3.8 Flash, are closing gaps through test-time scaling and efficiency gains. Trader sentiment reflects the tight 4-month window to December 31, where incremental Elo climbs from new versions or reasoning modes could push past typical thresholds, tempered by historical release cadence variability and the widening closed-versus-open model divide. Key catalysts include further Q4 launches from major labs and sustained leaderboard voting volume.