Code & Software Engineering
Epoch live leaderboardSWE-bench Verified
Human-validated software engineering issues from real-world Python repositories.
Metric
Accuracy
Results shown
33
Publisher
Epoch AI live leaderboard
Snapshot
Fetched 2026-10-08T23:19:31.697Z
33 of 33 models
33 of 33 models
Higher is better
List bars visualize relative performance. Plot bars use published 0–100 scores, shrink to a 1.5rem minimum, then scroll horizontally.
Scores are published snapshots and are only comparable within the same benchmark, version, metric, and evaluation configuration.