Deepdive
DeepDive QA RL environment with a Serper-powered search tool
- Domain
- rl-env
- License
- unknown
- Published
- Oct 2025
Cite
Notes
Only stored in your browser.
Top score 66.7% by GPT-5 Mini - 3 models reporting (2 frontier)
Score history
2Top models
3
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Deepdive?
- DeepDive QA RL environment with a Serper-powered search tool
- What is the current top score on Deepdive?
- The top reported score is 66.7% by GPT-5 Mini, across 3 models reporting (2 from frontier labs).
- How can a model improve its Deepdive score?
- Tools linked to Deepdive on Sophon include Deepdive RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
- What license is Deepdive under?
- Deepdive is available under unknown.