Contributed by the Risk Threshold Forecasting community.
Question
When will 80% accuracy be achieved on Cybench by a Llama 4 Behemoth scale model by Meta?
Total Forecasters0
Community Prediction
Make a Prediction
CDF
Quartiles | community | My Prediction |
lower 25% | ... | — |
median | ... | — |
upper 75% | ... | — |
Upper bound | ||
>Jun 2040 | — | — |
No key factors yetAdd some that might influence this forecast.
Add key factor
Authors:
Opened:Jun 25, 2025
Closes:Jan 1, 2041
Scheduled resolution:Jan 1, 2041
Spot Scoring Time:Jan 1, 2041
Authors:
Opened:Jun 25, 2025
Closes:Jan 1, 2041
Scheduled resolution:Jan 1, 2041
Spot Scoring Time:Jan 1, 2041