WARNING: THIS SITE IS A MIRROR OF GITHUB.COM / IT CANNOT LOGIN OR REGISTER ACCOUNTS / THE CONTENTS ARE PROVIDED AS-IS / THIS SITE ASSUMES NO RESPONSIBILITY FOR ANY DISPLAYED CONTENT OR LINKS / IF YOU FOUND SOMETHING MAY NOT GOOD FOR EVERYONE, CONTACT ADMIN AT ilovescratch@foxmail.com
Skip to content

Commit 44e7189

Browse files
authored
Merge pull request #12 from sebastianpinedaar/patch-1
Update README.md with the correct sizes for PolyBench-verified
2 parents 4eb5216 + 84127d7 commit 44e7189

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ Hello! We are delighted to announce SWE-PolyBench! A multi language repo level s
1515
- After receiving valuable feedback about our verified split, we updated the `Dockerfile` column for some instances and ensured that the pre-built images result in a 100% pass rate on the gold patch.
1616
- We removed two duplicate-like entries from the Java split of SWE-PolyBench_Verified
1717
* **08/27/2025**
18-
- **SWE-PolyBench Verified Split Released** - We have released the SWE-PolyBench Verified split with curated annotations containing 394 samples (72 Java, 100 JavaScript, 122 Python, and 100 TypeScript instances). The annotations are available in `data/annotations.jsonl` for enhanced evaluation and analysis. Check out the updated [leaderboard](https://amazon-science.github.io/SWE-PolyBench/).
18+
- **SWE-PolyBench Verified Split Released** - We have released the SWE-PolyBench Verified split with curated annotations containing 382 samples (72 Java, 100 JavaScript, 113 Python, and 100 TypeScript instances). The annotations are available in `data/annotations.jsonl` for enhanced evaluation and analysis. Check out the updated [leaderboard](https://amazon-science.github.io/SWE-PolyBench/).
1919

2020
- **Pre-built Docker Images Support** - We merged [PR #8](https://github.com/amazon-science/SWE-PolyBench/pull/8) which enables instant use of pre-built Docker images, significantly reducing setup time and improving the evaluation experience.
2121

0 commit comments

Comments
 (0)