keystone-bench
by xinxuxin (personal account)
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench. (description from the project’s GitHub page)
Repository facts
- Stars
- 799
- Forks
- 3
- Open issues and pull requests
- 0
- Primary language
- Python
- License
- Other license
- Owner
- xinxuxin · Personal account
- Created
- Sep 7, 2026
- Last push
- Sep 15, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 8,237: HowieHwong/TrustLLM
[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs an…
632 starsPythonMITLast push Oct 4, 2026
Rank 8,544: onyx-dot-app/EnterpriseRAG-Bench
Dataset and benchmark for RAG on company internal documents.
599 starsMITLast push Sep 3, 2026
Rank 5,837: TIGER-AI-Lab/ClawBench
Open-source benchmark for browser AI agents on daily tasks.
1,071 starsPythonApache-2.0Last push Oct 17, 2026
Rank 1,795: EvolvingLMMs-Lab/lmms-eval
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
4,456 starsPythonOther licenseLast push Oct 17, 2026
Rank 7,773: google-deepmind/long-form-factuality
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
695 starsPythonOther licenseLast push Jun 18, 2026
Rank 7,840: EverMind-AI/SkillCorpus
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
686 starsPythonApache-2.0Last push Oct 15, 2026