CommunityFact: leaderboard
Misinformation verification increasingly occurs in public, fast-moving, and multilingual online settings, where static benchmarks provide an incomplete measure of model reliability. We introduce CommunityFact, a refreshable benchmark for misinformation detection in the wild, with three major goals: coverage, granularity, and redistributability. This release contains 15,992 standalone claims across
Metric: Overall (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | aya-expanse-32B | 69.93 | #692 |
| 2 | Gemini 2.5 Flash | 68.01 | #245 |
| 3 | Qwen 3 32B | 65.68 | #443 |
| 4 | aya-expanse-8B | 63.74 | #931 |
| 5 | Qwen 3 14B | 62.83 | #537 |
| 6 | Grok 4.3 | 53.85 | #188 |
| 7 | EuroLLM-9B | 46.46 | #1254 |
| 8 | GPT-5 Nano | 38.09 | #425 |
| 9 | Ministral 8B | 36.74 | #1040 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=communityfact · How It Works · Data refreshed daily, snapshot 2026-10-20.