ScienceAgentBench (ICLR 2025)

github.com/osu-nlp-group/scienceagentbench
Active150updated 1 month ago
Python
MIT

102 executable tasks from 44 peer-reviewed papers across 4 disciplines with containerized evaluation

Sourced from

  • GitHubgithub.com/osu-nlp-group/scienceagentbench
  • Awesome AI for Sciencegithub.com/osu-nlp-group/scienceagentbench

Related resources

LLM agents across scientific domains

Idle971 year ago
MIT

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science with 140+ ready-to-use skills and 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Antigravity, and the open Agent Skills standard (K-Dense-AI, 26K+ stars, 2025)

Active34.3K1 day ago
Python
MIT

Comprehensive collection of 125+ ready-to-use scientific skill modules for Claude AI across bioinformatics, cheminformatics, clinical research, ML, and materials science

Active31.4K1 month ago
Python
MIT

Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models (857+ stars, 2026)

Active8743 weeks ago
HTML
AGPL-3.0

Curated scientific LLM papers (260+ models)

Idle6611 year ago
MIT

Multi-LLM consensus framework for automated cell type annotation in single-cell transcriptomics, integrating predictions from 10+ large language models with iterative discussion and uncertainty quantification to reduce single-model biases, achieving up to 95% accuracy without reference datasets; available as CRAN R package and PyPI Python package with Scanpy/Seurat integration (2025)

Active6571 week ago
Python
MIT