# benchmark_compare

> Read benchmark compare: Is the ONLY valid arm-vs-arm test: it pairs the two models on the items BOTH completed, and answers rescue and damage counts with an exact-McNemar p..

- Type: Skill
- Publisher: Hanzo
- Category: benchmark
- Price: Free to read
- SHA-256: cc28a9fa3286de6f471f536d942e85258984815a693daf3d008199e54f76c6cd

## Links

- [SKILL.md](https://api.hanzo.ai/.well-known/agent-skills/benchmark_compare/SKILL.md)

---

Page: https://hanzo.market/skills/benchmark_compare · Every listing: https://hanzo.market/llms.txt