There is a newer version of the record available.

Published July 12, 2025 | Version v3

Execution-Feedback Driven Test Generation from SWE Issues

Authors/Creators

Description

We have shared 8 folders containing tests for 2 benchmarks (SWT-Bench Lite and TDD-Bench Verified), 2 models (GPT-4o and Claude-3.7-Sonnet), and 2 approaches (Otter and e-Otter). Each folder contains 10 tests using different prompting techniques (e.g., planner, full, standard) and associated logs.

Files

e-otter_lite_claude.zip

Files (2.8 GB)

Name Size
md5:5f4088a635563813fdce52d7ce638f4e
292.4 MB Preview Download
md5:d1d3a310679fb55dadd71ed43281342a
290.6 MB Preview Download
md5:ee439823ee3a45113c02716fa1814ada
392.6 MB Preview Download
md5:f67c1beff76cd7af8ee6869627cbeb14
418.2 MB Preview Download
md5:298f4ea22669f99fd5602426ae94cb5b
295.7 MB Preview Download
md5:87459d8f15af0bac110b4ee56f3c94cf
292.5 MB Preview Download
md5:c3e077b477cee0339354ef8da931a8cf
390.2 MB Preview Download
md5:29f64bba8c75e766643f1f448bc141c0
413.8 MB Preview Download