Will any AI model achieve a score of 94% or higher on the GPQA Diamond Benchmark Leaderboard before February 1, 2026?
This question is not yet open for predicting.
No key factors yetAdd some that might influence this forecast.
Authors:
Opens:Nov 22, 2025
Closes:Jan 31, 2026
Scheduled resolution:Feb 1, 2026
Spot Scoring Time:Nov 26, 2025
