Model Releases
3/3 We took 7 weak agents (ranks 7-13, none scoring >45) from the leaderboard & merged them into 1 report/task. Essentially boosting for dee…
3/3 We took 7 weak agents (ranks 7-13, none scoring >45) from the leaderboard & merged them into 1 report/task. Essentially boosting for deep research. The result: New #1 DRB II TotalScore of 64.38. F
3/3 We took 7 weak agents (ranks 7-13, none scoring >45) from the leaderboard & merged them into 1 report/task. Essentially boosting for deep research. The result: New #1 DRB II TotalScore of 64.38. Full write-up here: https://www.ai21.com/blog/merging-weak-agents-into-a-state-of-the-art-deep-researcher/?utm_source=org-twitter
Source: AI21 Labs (X) | 2026-06-24