What will be the highest score achieved on SWE-Bench Verified in 2025?
25
Ṁ1kṀ4.8kresolved Jan 3
1H
6H
1D
1W
1M
ALL
100%91%
70-85 inclusive
1.0%
<70
8%
>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.
Market context
Get 
1,000 to start trading!
1,000🏅 Top traders
| # | Trader | Total profit |
|---|---|---|
| 1 | Ṁ666 | |
| 2 | Ṁ265 | |
| 3 | Ṁ114 | |
| 4 | Ṁ102 | |
| 5 | Ṁ53 |
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
What will be the highest score on the SWE-bench pro private set before 2027?
68.0
Top SWE-Bench Pro score by Jan 1, 2027?
78.3
What will be the best GSOBench score by Dec 31, 2026?
Best SWE-Bench Pro public score by June 30, 2026
In what year will AI achieve a score of 95% or higher on the SWE-bench Verified benchmark?
11/27/27
When will SWE-bench be solved?
AI resolves at least X% on SWE-bench WITH assistance, by 2028?
AI resolves at least X% on SWE-bench without any assistance, by 2028?
Will Anthropic’s next Sonnet model exceed 83% on SWE-bench verified?
59% chance
BIG-bench accuracy 75% #5: Will SOTA for a single model on BIG-bench pass 75% by the start of 2028?
87% chance