Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.
Shell · active 2025-02-25 → 2026-06-14 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 475 days from 2025-02-25 to 2026-06-14. Pushes: 159 total, peak 14 in a day. Pull requests: 209 total, peak 11 in a day. Issues: 52 total, peak 7 in a day. Comments: 403 total, peak 26 in a day. Stars: 52 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| john-b-yang | 415 | 124 | 88 | 184 |
| ofirpress | 53 | 2 | 7 | 39 |
| klieret | 48 | 29 | 3 | 9 |
| zhimin-z | 24 | 0 | 0 | 13 |
| xingyaoww | 9 | 0 | 4 | 4 |
| bytedance-se-research | 9 | 0 | 5 | 4 |
| willfleury | 9 | 0 | 2 | 6 |
| dcloud347 | 8 | 0 | 4 | 3 |
| lugeng | 7 | 0 | 2 | 5 |
| THY-AI | 7 | 0 | 2 | 5 |
| aorwall | 6 | 0 | 5 | 1 |
| brokespace | 6 | 0 | 3 | 3 |
| chao-peng | 5 | 0 | 0 | 5 |
| tangken333 | 5 | 0 | 1 | 4 |
| OctoJax | 5 | 0 | 1 | 4 |
| cmsflash | 5 | 0 | 2 | 3 |
| m990m1 | 5 | 0 | 0 | 5 |
| crhf | 5 | 0 | 3 | 2 |
| UbeCc | 5 | 0 | 1 | 4 |
| adityasoni9998 | 4 | 0 | 1 | 2 |
Recent activity
Latest issues, pull requests and releases
- Pull request#450acewhitegui2026-06-14 10:35
- Issue comment#442piyushhhxyz2026-04-20 21:34Add 100xflux (Claude Sonnet 4.6) — 363/500 (72.60%) on SWE-bench Verified
- Issue#437Talha7712026-04-05 02:37How to access the predictions
- Pull request#432lingxi-agent2026-03-28 23:53
- Issue#425thimytran689-tech2026-03-08 03:40Request access to trajectory logs
- Issue comment#346ZhongQiangDev2026-03-03 08:10Add new submission for SWE-bench Multimodal evaluation 20251012_RepoRepair_claude-sonnet-4-20250514
- Pull request#424aorwall2026-02-27 16:59
- Pull request#423aorwall2026-02-26 20:48
- Pull request#423aorwall2026-02-26 17:07
- Pull request#414aorwall-frankpenny2026-02-18 09:06
- Pull request#412Chesars2026-02-09 18:51
- Pull request#410Benkovichnikita2026-02-07 21:31
- Issue comment#397dhirenmathur2026-01-27 14:54Add results for SWE-Bench Lite for Potpie AI
- Issue comment#406Chesars2026-01-26 22:51Update agent display names to include models
- Pull request#406Chesars2026-01-26 20:05
- Issue#396john-b-yang2026-01-26 04:43MaximusAI Submission
- Issue comment#393john-b-yang2026-01-26 04:43Add 20251219 Sonar Foundation Agent full SWE-bench
- Issue comment#383john-b-yang2026-01-26 04:11cmccjoinaicode swebenchlite submission
- Issue comment#371john-b-yang2026-01-26 04:1120251120 cmccjoinaisdk submission
- Issue comment#363john-b-yang2026-01-26 04:07SWE-bench Lite submission for the best-belief agent discovered by Huxley-Gödel Machine
- Pull request#394crhf2026-01-26 04:06
- Issue comment#394john-b-yang2026-01-26 04:05Add 20251205_sonar-foundation-agent_claude-opus-4-5 on Verified
- Issue comment#394crhf2026-01-26 02:48Add 20251205_sonar-foundation-agent_claude-opus-4-5 on Verified
- Issue comment#329john-b-yang2026-01-26 02:4220250907 - Add results for SWE-Swiss-32B
- Issue comment#397john-b-yang2026-01-26 02:40Add results for SWE-Bench Lite for Potpie AI
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 52 stars here means stars gained during the window, not the repo's star count.