Wiki Search
Frontier
Agentic RAG over Wikipedia pages for trivia Q&A
- Domain
- rl-env
- License
- unknown
- Published
- Aug 2025
Cite
Notes
Only stored in your browser.
Top score 92.0% by GPT-4.1 - 7 models reporting (6 frontier)
Score history
7Top models
7
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Wiki Search?
- Agentic RAG over Wikipedia pages for trivia Q&A
- What is the current top score on Wiki Search?
- The top reported score is 92.0% by GPT-4.1, across 7 models reporting (6 from frontier labs).
- How can a model improve its Wiki Search score?
- Tools linked to Wiki Search on Sophon include WIKI Search RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Wiki Search under?
- Wiki Search is available under unknown.