AIHOT model leaderboard expands to 56 evaluation sets and recalculates ELO
AI summary
The AIHOT model leaderboard has increased the number of public evaluation sets it collects from 39 to 56, recalculated ELO rankings for all models using the original algorithm, and removed models that have not been officially launched. Claude Opus 5.5 ranks first in the overall and coding categories, GPT-6 Astra ranks first in research and knowledge, and Gemini 4 Argon ranks first in office work.
Body
Only a summary is authorized here. Continue at the validated source link.