Contributed by the Risk Threshold Forecasting community.
When will 75% accuracy be reached on LAB-Bench Cloning Scenarios by a Claude Opus 4 scale model by Anthropic?
Current estimate
Key Factors
No key factors yetAdd some that might influence this forecast.
Add key factor
No forecasts yet
Forecast Timeline
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:Jun 28, 2025
Learn more about Metaculus NewsMatch
When will Anthropic reach or surpass ASL-4?
19 Apr 2030
(27 Nov 2027 - Feb 2035)
19 Apr 2030
(27 Nov 2027 - Feb 2035)
8 forecasters
When will Anthropic first report that an AI system reached or surpassed CBRN risk level 4?
16 Oct 2027
(24 Oct 2026 - Nov 2031)
16 Oct 2027
(24 Oct 2026 - Nov 2031)
3 forecasters
When will an AI achieve an score of 1.5 or higher in the RE-bench at any time budget between 8h and 32h?
17 Oct 2027
(10 Jan 2027 - 26 Nov 2028)
17 Oct 2027
(10 Jan 2027 - 26 Nov 2028)
44 forecasters