
What will be the highest score achieved on SWE-Bench Verified in 2025?
23
1kṀ4536Jan 2
1H
6H
1D
1W
1M
ALL
1%
<70
90%
70-85 inclusive
9%
>85
https://openai.com/index/introducing-swe-bench-verified/
https://www.swebench.com/
Highest performance reported before 2026. Any run on https://www.swebench.com/ counts. Large AI company reported numbers count whether or not they're listed on swebench.com Other claimed scores will generally not be counted unless verified by a third party.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
Sort by:
@JacobPfau Does Introducing Codex resolve <70 NO? Very annoyingly they don't give a number, but in the plot codex-1 pass@1 is clearly above 70%.
@SanghyeonSeo Don't see an option to resolve individual options, IIRC there are two types of multiple choice questions
People are also trading
Related questions
Top SWE-Bench Verified score in 2025?
78.6
What will be the best performance on SWE-bench Verified by December 31st 2025?
Top SWE-Bench Pro public dataset score by January 1, 2026
62.1
Best Lab on SWE-Bench Verified EOY 2025
What will be true of the SOTA AI on the FrontierMath benchmark, before 2026?
Best SWE-Bench Pro public score by June 30, 2026
Top Multi-SWE-bench score in 2025?
37.1
In what year will AI achieve a score of 95% or higher on the SWE-bench Verified benchmark?
12/5/27
What will be the best normalized score achieved on the original 7 RE-Bench tasks by December 31st 2025?
Will SotA on PaperBench (Code-Dev) surpass 75% in 2025?
14% chance
