awesome-code-benchmark
github.com/tongye98/awesome-code-benchmark ↗A comprehensive code domain benchmark review of LLM researches.
236
GitHub Stars
229
Curated Resources
2
Categories
17 hours ago
Last Refreshed
Surveys🚀 Benchmark Categories
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me program repair, testing & debugging resources from awesome-code-benchmark"
Installation instructions →What's inside
🚀 Benchmark Categories
- A11YRepair: Bridging Web Accessibility Barriers via Knowledge-Enhanced Divide-and-Conquer RepairProgram Repair, Testing & Debugging
- Advancing vision-language models in front-end development via data synthesisFrontend, UI & Visual-Interactive Development
- AInsteinBench: Benchmarking Coding Agents on Scientific RepositoriesRepository & Agentic Software Engineering
- aiXamine: Simplified LLM Safety and SecuritySecurity, Reliability & Robustness
- A Large-scale Class-level Benchmark Dataset for Code Generation with LLMsCode Generation & Completion
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTSProgram Repair, Testing & Debugging
Showing a sample of 229 resources. View the full list on GitHub →