- Will any AI model reach a Chatbot Arena score of at least 1550 by December 31?14¢
- Will any AI model reach a Chatbot Arena score of at least 1600 by December 31?7¢
- Will any AI model reach a Chatbot Arena score of at least 1650 by December 31?7¢
- Will any AI model reach a Chatbot Arena score of at least 1700 by December 31?3¢
- Will any AI model reach a Chatbot Arena score of at least 1530 by December 31?50¢
- Will any AI model reach a Chatbot Arena score of at least 1520 by December 31?95¢
- Will any AI model reach a Chatbot Arena score of at least 1540 by December 31?41¢
This market will resolve to "Yes" if any model on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) reaches at least the specified Arena Score by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No". Results from the 'Score' section on the 'Text Arena' Leaderboard tab (https://lmarena.ai/leaderboard/text), with the style control unchecked, will be used to resolve this market. The resolution source is the Chatbot Arena LLM Leaderboard (https://lmarena.ai/). If this source is temporarily unavailable, the market remains open until it is accessible again; if permanently unavailable, this market will resolve to "No".
Recent releases from Anthropic, including Claude Fable 5 and Opus 5 variants, have anchored the top of the LMSYS Arena overall leaderboard near 1505–1508 Elo, with tight clustering among Google’s Gemini 3.8 Flash (1494), Meta’s Muse Spark, and Chinese models like Alibaba’s Qwen3.8-Max and Moonshot’s Kimi K3. Fresh updates such as Qwen3.8-Max-0902’s 1691-point Code Arena WebDev debut and Gemini 3.8 Flash gains in agentic and multi-turn tasks underscore accelerating specialization in coding and reasoning benchmarks. With four months remaining, trader sentiment hinges on whether frontier labs sustain monthly Elo gains through new post-training or larger context windows before year-end deadlines, amid competitive pressure from open-weight contenders and typical slippage risks in model timelines.