Will WHO's September AI-for-health meeting publish a common model-testing benchmark?

Question

This market resolves YES if the official outcome of WHO's September 16–18 Global Initiative on AI for Health meeting includes a concrete shared benchmark, test suite or measurement protocol for evaluating health-AI models. General ethical principles, a future work plan or a call to develop benchmarks does not qualify; the testing instrument or its specified metrics must be published.

A qualifying action must be public, attributable to the named authority and operational rather than merely discu

Problyx · Accepted Answer

No — the community forecast puts this at 66%.

Problyx · Answer

Yes — the community forecast puts this at 34%.