Will GPT-5 exceed 70% on WebArena?
20
Ṁ100Ṁ694resolved Jan 10
Resolved
N/A1H
6H
1D
1W
1M
ALL
The current high score is ChatGPT Agent's 65.4%

This question is managed and resolved by Manifold.
Market context
Get
1,000 to start trading!
Sort by:
https://docs.google.com/spreadsheets/d/1M801lEpBbKSNwP-vDBkC_pF7LdyGU1f_ufZb_NWNBZQ/edit?gid=0#gid=0
Doesn't look like anybody has run GPT-5 on WebArena yet