This market resolves to the AI model that achieves the highest overall score on the AiderBench evaluation in May on the leaderboard [here](https://aider.chat/docs/leaderboards/). Rankings with two models will not qualify
Update 2025-05-20 (PST) (AI summary of creator comment): The creator has clarified a condition for model eligibility:
A model must be evaluated on AiderBench by the end of May to be considered.
If a model is not evaluated by this deadline, it will not qualify, and the market will resolve based on the models that meet this and other existing criteria.
1,000People are also trading
@joanna What if unofficial evaluations exist that say that Google's model is better, but don't appear on the official website
@theshortbread Like if someone runs AiderBench on their own and finds a better result? I could be wrong here but I don't think the numbers replicate perfectly (see their Qwen3 write-up), so I would be inclined to not consider it