KOPA-Bench
Explore score history ↗Evaluates multi-step tool-calling over Korean open public APIs with 145 real-world tasks, designed to measure performance gaps in open-source LLM agents that chain tool calls across live government APIs.
- Released
- 2026-09-04
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
KOPA-Bench paper
No reported scores are on record for this benchmark yet.