Terminal-Bench Science (Harbor Framework, 2026)

github.com/harbor-framework/terminal-bench-science
Active201updated 12 hours ago
Python
Apache-2.0

Benchmark evaluating AI agents on complex real-world scientific workflows in terminal environments across life, physical, earth, and mathematical sciences; featured on model cards for Claude Opus 4.7, GPT-5.5, and Gemini 3.1 Pro (200+ stars, Apache 2.0)

Sourced from

  • Awesome AI for Sciencegithub.com/harbor-framework/terminal-bench-science
  • GitHubgithub.com/harbor-framework/terminal-bench-science

Related resources

Benchmark evaluating AI agents for end-to-end automated research from re-discovery to new-discovery, with 40 real-science tasks across 10 disciplines, curated datasets from published papers, and expert-curated multimodal rubrics (170+ stars, MIT License)

Active1723 weeks ago
Jupyter Notebook
MIT

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

Active1412 months ago
Python
MIT

Multimodal deep learning framework integrating peptide-MHC protein sequence, structure, and biochemical properties to predict class-I immunogenicity for infectious disease epitopes and cancer neoepitopes with cancer-wildtype contrastive learning, enabling personalized vaccine design (Krishnaswamy Lab, Yale University)

Active464 months ago
Python
NOASSERTION

Parallel symbolic regression network evaluating millions of expressions on GPU with automated subtree reuse, Nature Computational Science cover article (MIT, 2026)

Active222 months ago
Python
MIT

Advanced OCR with PP-StructureV3 document parsing, 13% accuracy improvement, supports 80+ languages

Active85.8K6 days ago
Python
Apache-2.0

SOTA multimodal document parsing with 1.2B parameters outperforming GPT-4o, converts PDFs to LLM-ready Markdown/JSON

Active74.3K1 week ago
Python
NOASSERTION