facebookresearch/llm-speedrunner

Benchmark for LLM agents reproducing scientific findings

View on index · View in 3D Map

Related repos

• Benchmark for LLMs on software engineering tasks
• Benchmark for evaluating LLMs on real-world GitHub issues
• Benchmark evaluates LLMs as agents
• Benchmarks LLMs for end-to-end machine learning workflows
• System using LLM agents for LLM discovery
• evaluate and track LLM experiments and AI agents
• Pipeline turns social posts into LLM training datasets
• Unified environment for developing and testing LLM agents with feedback
• Open-source platform for evaluating and optimizing LLM apps
• Framework for evaluating LLM agents in Factorio