Beyond the Leaderboard: Multi-Dimensional Evaluation of Dense and Mixture-of-Experts Models for Automated Program Repair
cs.SE, cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/anvishah1/MoE-vs-dense--model-for-APR
Sources
- A Comprehensive Study of Automatic Program Repair on the QuixBugs Benchmark
- Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs
- Qwen2.5-Coder Technical Report
- DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
- Evaluating Large Language Models Trained on Code
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties