InternScience / SGI-Bench
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Why this job: topics: evaluation, benchmark
What it does
Scientist-aligned benchmark for evaluating Scientific General Intelligence (SGI) across the full inquiry cycle: Deliberation, Conception, Action, and Perception. The benchmark spans 10 disciplines and more than 1,000 expert‑curated samples inspired by Science’s 125 Big Questions, with an agentic evaluation framework and multi‑metric protocol.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 5 months ago
- Stars
- 172
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| OpenDCAI / One-Eval | 165 | 2 months ago | Apache-2.0 | No downloads |
| cxcscmu / IdeaTaste | 31 | 6 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- agent
- ai
- ai-scientist
- ai4science
- automated-science
- benchmark
- code-gen
- code-generation
- deep-research
- evaluation
- idea-generation
- llm
Project record
- JobEvals and observability
- StatusListed
- Commits54
- Forks4
- Watching2
- Stars in 28 days0
- CreatedDec 3, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026