SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
active 2025-09-05 → 2026-06-14 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 283 days from 2025-09-05 to 2026-06-14. Pushes: 42 total, peak 3 in a day. Pull requests: 39 total, peak 15 in a day. Issues: 43 total, peak 7 in a day. Comments: 63 total, peak 13 in a day. Stars: 137 total, peak 31 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 |
|---|---|---|---|---|
| jeff-da | 72 | 25 | 7 | 26 |
| dependabot[bot] | 22 | 0 | 19 | 3 |
| 18vijayb | 22 | 14 | 3 | 3 |
| knkgrg | 7 | 2 | 2 | 1 |
| arktrail | 6 | 0 | 0 | 4 |
| prabhuteja12 | 5 | 0 | 1 | 3 |
| kevinlin311tw | 4 | 0 | 0 | 3 |
| orreroing | 3 | 0 | 0 | 3 |
| volkov | 3 | 0 | 2 | 1 |
| cslsolow | 3 | 0 | 0 | 1 |
| zhimin-z | 3 | 0 | 0 | 0 |
| meitalbensinai | 2 | 0 | 0 | 1 |
| socket-security[bot] | 2 | 0 | 0 | 2 |
| JonathanGabor | 2 | 0 | 1 | 0 |
| jhmblundin | 2 | 0 | 1 | 0 |
| jtmcg | 2 | 0 | 0 | 0 |
| jonggunp | 2 | 0 | 0 | 0 |
| pedropnaves | 2 | 0 | 1 | 0 |
| Xander23333 | 2 | 0 | 0 | 1 |
| UbeCc | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#93ConnorBAdams2026-04-29 01:26Git Reward Hacking in SWEBench Pro OSS
- Issue#82gokulr-cerebras2026-03-24 09:32Config file to be used for swebench submission
- Pull request#77pedropnaves2026-02-28 15:46
- Issue#76pedropnaves2026-02-28 15:46Test name mismatches cause false negatives in eval scoring (whitespace + truncated quotes in fail_to_pass)
- Issue#74jeff-da2026-02-11 23:12Patches with binary hunks fail to apply
- Issue#74StephenGrider2026-02-11 21:01Patches with binary hunks fail to apply
- Issue comment#71jeff-da2026-02-09 20:21Inconsistency between HuggingFace dataset and instance-info.txt
- Issue#72jeff-da2026-02-09 20:21Time-sensitive test causes false negative in one instance
- Pull request#73jhmblundin2026-02-08 02:57
- Issue#70JosephZZ2026-01-15 08:04ever tested over Claude Code?
- Issue#65jeff-da2026-01-07 20:36Missing Docker images for 8 (Probably more) instances on jefzda/sweap-images
- Pull request#67jeff-da2026-01-07 20:36
- Pull request#67jeff-da2026-01-07 20:36
- Pull request#67jeff-da2026-01-07 20:35
- Issue#23jeff-da2026-01-06 23:00Frequent timeouts on tutoa problems
- Issue comment#23jeff-da2026-01-06 23:00Frequent timeouts on tutoa problems
- Issue#65jhmblundin2025-12-31 01:25Missing Docker images for 8 (Probably more) instances on jefzda/sweap-images
- Issue comment#64jeff-da2025-12-24 18:44Reproducing Results with Mini Agent
- Issue comment#64meitalbensinai2025-12-17 11:46Reproducing Results with Mini Agent
- Issue#46jeff-da2025-12-17 01:41config/tool_use.yaml: tool use prompt for python code repository
- Issue comment#48jeff-da2025-12-11 19:23jeff_tool.yaml missing
- Issue comment#63jeff-da2025-12-11 19:21Submitting to leaderboard
- Pull request#62volkov2025-11-22 13:51
- Pull request#62volkov2025-11-22 13:51
- Issue comment#61volkov2025-11-22 13:32Claude/random datapoint 01 auz9qp twh zy g3 n kpw rg n2o
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 137 stars here means stars gained during the window, not the repo's star count.