GitHub · Python
InternScience/SGI-Bench
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
- Stars
- 173
- Forks
- 4
- Stars gained in 24 hours
- +7
- Forks gained in 24 hours
- 0
Topics: agent, ai, ai4science, benchmark, llm, code-generation, wet-lab-protocols, deep-research, idea-generation, multi-modal
Latest data point: Nov 20, 2026 · 173 stars · 4 forks