Benchmark RadarAI BENCHMARK PROFILE
CommunityFact
CommunityFact evaluates misinformation detection on 15,992 claims across five languages and two domains, using accuracy against human Community Notes ratings as the scoring metric.
- Released
- 2026-05-28
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Static benchmarks fail to capture dynamic, multilingual misinformation settings. CommunityFact provides a refreshable benchmark to assess model reliability in real-world verification contexts.
Motivation
Misinformation verification increasingly occurs in public, fast-moving, and multilingual online settings, where static benchmarks provide an incomplete measure of model reliability.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.