FrenchNews-7 (Unseen Outlets): leaderboard
Metric: Mean per-class recall (%; seven editorial desks, Politique, International, Culture & Loisirs, Sport, Sciences & Technologies, Société and Économie, on a balanced 2,100-article pool of 300 per desk from four outlets never seen in training (Libération, BFMTV, Le Nouvel Obs, Franceinfo), gold labels from publisher URL slugs; equals accuracy on the balanced pool; zero-shot prompt with one-sentence desk definitions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.3 70B Instruct | 77.8 |
| 2 | Mistral Small 3.2 | 77.2 |
| 3 | GPT-OSS-120B | 75.3 |
Interactive version: theaggregate.ai/benchmark?slug=frenchnews-7-unseen-outlets · How It Works · Data refreshed daily, snapshot 2026-09-29.