GAUGE Benchmark
Explore score history ↗GAUGE evaluates agent-built financial valuation models against observed analyst practice using 56 facets, eight validity gates, and a failure-aware score over 196 tasks.
- Released
- 2026-07-27
- Institutions
- StepFun AI (China) · Tsinghua University · Shanghai Jiao Tong University
- Evaluates
- Agents, Finance, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
GAUGE paper
No reported scores are on record for this benchmark yet.