smallcloudai / refact-benchLinks
A benchmarking tool for evaluating AI coding assistants on real-world software engineering tasks from the SWE-Bench dataset.
☆53Updated 2 months ago
Alternatives and similar repositories for refact-bench
Users that are interested in refact-bench are comparing it to the libraries listed below
Sorting:
- ☆109Updated 2 months ago
- Enhancing AI Software Engineering with Repository-level Code Graph☆207Updated 5 months ago
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆302Updated this week
- Data and evaluation scripts for "CodePlan: Repository-level Coding using LLMs and Planning", FSE 2024☆74Updated last year
- ☆53Updated 7 months ago
- CodeSage: Code Representation Learning At Scale (ICLR 2024)☆112Updated 10 months ago
- ☆98Updated 11 months ago
- Coding problems used in aider's polyglot benchmark☆175Updated 8 months ago
- Harness used to benchmark aider against SWE Bench benchmarks☆71Updated last year
- Scaling Data for SWE-agents☆386Updated last week
- Run SWE-bench evaluations remotely☆41Updated 3 weeks ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆92Updated 3 months ago
- RepoQA: Evaluating Long-Context Code Understanding☆115Updated 10 months ago
- [FORGE 2025] Graph-based method for end-to-end code completion with context awareness on repository☆65Updated last year
- A better way of testing, inspecting, and analyzing AI Agent traces.☆40Updated last month
- [NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation☆54Updated last week
- Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions☆47Updated this week
- [ACL25' Findings] SWE-Dev is an SWE agent with a scalable test case construction pipeline.☆55Updated last month
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆61Updated 8 months ago
- Official implementation of paper How to Understand Whole Repository? New SOTA on SWE-bench Lite (21.3%)☆92Updated 5 months ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)☆84Updated 5 months ago
- A Text-Based Environment for Interactive Debugging☆258Updated this week
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆208Updated last week
- ☆37Updated 3 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆23Updated last week
- Guardrails for secure and robust agent development☆342Updated last month
- Pivotal Token Search☆123Updated last month
- Controlled text generation with programmable constraints☆130Updated this week
- Contains the prompts we use to talk to various LLMs for different utilities inside the editor☆80Updated last year
- A framework for optimizing DSPy programs with RL☆151Updated last week