Role: UMA Voter Task: Resolve the market based strictly on official data from the…
- User
Role: UMA Voter Task: Resolve the market based strictly on official data from the designated source.
Market Description and Rules:
This market will resolve to "Yes" if any model by DeepSeek has a higher arena score than all OpenAI models on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) at any point by May 31, 2025 at 11:59 PM ET. Otherwise, this market will resolve to "No".
Note that the arena score must be higher - if it ties with the best OpenAI arena score it will not count.
The resolution source for this market is the Chatbot Arena LLM Leaderboard found at https://lmarena.ai/. If this resolution source becomes unavailable, the market will remain open until it is accessible again. If it becomes permanently unavailable, resolution will be based on another credible source.
Assistant
Based on the market description and rules, the market will resolve to "Yes" if any DeepSeek model achieves a higher arena score than all OpenAI models on the Chatbot Arena LLM Leaderboard (https://lmarena.ai/) at any point by May 31, 2025, 11:59 PM ET. Otherwise, it will resolve to "No". The specified resolution source is the Chatbot Arena LLM Leaderboard.
According to the Chatbot Arena Leaderboard data available as of April 23, 2025[1]:
- The DeepSeek model with the highest Arena Elo score is
DeepSeek-V3-0324at 1373. - Among OpenAI models, the highest Arena Elo score is held by
o3-2025-04-16at 1418[1]. Other OpenAI models listed includeChatGPT-4o-latest (2025-03-26)at 1408,GPT-4.5-Previewat 1398,GPT-4.1-2025-04-14at 1363,o4-mini-2025-04-16at 1351,o1-2024-12-17at 1350,o3-mini-highat 1325, andGPT-4.1-mini-2025-04-14at 1322[1].
Comparing the scores from this snapshot, the highest DeepSeek score (1373) is not higher than the highest OpenAI score (1418)[1].
Previous snapshots and mentions from search results show DeepSeek models, such as DeepSeek-R1 and DeepSeek V3, ranking competitively but still below the top OpenAI models like GPT-4o[2][3][4]. For example, in late January/early February 2025, DeepSeek-R1 was noted as being ranked 3rd or 4th overall, with a score slightly below ChatGPT-4o[3][4][5].
Based on the latest available data from the specified source (April 23, 2025), the condition for this market to resolve to "Yes" has not yet been met.
However, the market resolution date is May 31, 2025. The final resolution depends on whether a DeepSeek model's score surpasses all OpenAI models' scores on the Chatbot Arena leaderboard at any point between now and the deadline.
As of the current date and based on the provided data up to April 23, 2025, the market condition for a "Yes" resolution has not been fulfilled. The market's final resolution remains pending until the May 31, 2025 deadline has passed and the leaderboard status throughout the market's term is confirmed.
- The DeepSeek model with the highest Arena Elo score is
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.