InternScience / ResearchClawBench
🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
Why this job: topics: evaluation, benchmark
What it does
ResearchClawBench is a benchmark that measures whether AI coding agents can independently conduct scientific research — from reading raw data to producing publication-quality reports — and then rigorously evaluates the results against real human-authored papers.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 13 days ago
- Stars
- 277
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Jupyter Notebook
- 34% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 3 merged
- 1 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| suyoumo / ClawProBench | 830 | 2 months ago | Apache-2.0 | No downloads |
| comet-ml / opik-openclaw | 723 | 36 days ago | Apache-2.0 | No downloads |
| AMAP-ML / LoopArena | 154 | 27 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Jupyter Notebook 34%
- Python 22%
- JavaScript 19%
- TeX 9%
Topics
- agent
- ai
- ai-agent
- ai-scientist
- ai4science
- auto-research
- benchmark
- claude
- claude-code
- clawdbot
- codex
- discovery
Project record
- JobEvals and observability
- StatusListed
- Commits196
- Forks29
- Watching1
- Stars in 28 days+12
- CreatedMar 18, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026