Benchmark
git_bisect
12 fixtures
Model Leaderboard
Models ranked by pass rate on git_bisect. A model that dominates overall might rank lower here. That's the point.
Loading...
Tags
git-bisect (12)
linear-history (6)
branching (5)
multi-file (3)
regression (2)
recent-bug (1)
basic (1)
middle-commit (1)
near-end (1)
early-commit (1)
second-commit (1)
third-commit (1)
branching-history (1)
merge (1)
main-branch (1)
validation (1)
import-error (1)
complex (1)
frontend (1)
backend (1)
Per-Fixture Comparison
Loading...