Spiral Bench
Multi-turn text-based environment for evaluating agents on the Spiral-Bench dataset.
- Domain
- rl-env
- License
- unknown
- Published
- Sep 2025
Cite
Notes
Only stored in your browser.
Top score 0 by GPT-4.1 Mini - 2 models reporting (2 frontier)
Score history
2Top models
2
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Spiral Bench?
- Multi-turn text-based environment for evaluating agents on the Spiral-Bench dataset.
- What is the current top score on Spiral Bench?
- The top reported score is 0 by GPT-4.1 Mini, across 2 models reporting (2 from frontier labs).
- How can a model improve its Spiral Bench score?
- Tools linked to Spiral Bench on Sophon include Spiral Bench RL Env (Prime Intellect) - RL environments, datasets, and scaffolds that target this eval.
- What license is Spiral Bench under?
- Spiral Bench is available under unknown.