AIHOT Model Leaderboard Expands Evaluation Set to 56 and Recalculates ELO
AI summary
The AIHOT model leaderboard has increased the number of publicly available evaluation sets it scrapes from 39 to 56, and recalculated ELO rankings for all models using the original algorithm, while removing models that have not been officially released (such as Gemini 4 Carbon). The author states that this version of the rankings aligns well with their understanding of each model.
Body
Only a summary is authorized here. Continue at the validated source link.