benchmark · first seen 16 Oct 2026
SWE-bench-style repository benchmarking
Evaluating coding agents by having them make executable patches in real repositories verified by tests.
Mentions per week
PapersCodeDiscussion
Earliest sources
- MLOps-Bench: Benchmarking AI Agents on Production ML Engineering in Real RepositoriesPapers · 16 Oct 2026 · Quoc Co Tran, Hitesh Laxmichand Patel, Diwakar Mahajan, Kshitij Bakliwal, Avi Si…
Latest sources
- MLOps-Bench: Benchmarking AI Agents on Production ML Engineering in Real RepositoriesPapers · 16 Oct 2026 · Quoc Co Tran, Hitesh Laxmichand Patel, Diwakar Mahajan, Kshitij Bakliwal, Avi Si…