CARTE - Bretagne: leaderboard
CARTE (Culturally Anchored Regional-Territorial Evaluation, 2026) is a French multiple-choice benchmark on regionally differentiated knowledge about France, with four answer options plus an I do not know option, evaluated 0-shot. This board is accuracy in percent on the 145 questions about Brittany (Bretagne); higher is better.
Metric: Accuracy (%) on the 145 CARTE questions about Bretagne, 0-shot, five options per question (four answers and 'Je ne sais pas', which scores as wrong); questions generated by Gemini 3 Flash from human-selected French documents and filtered; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 96.2 | #164 |
| 2 | Gemma 3 12B (IT) | 82.1 | #1837 |
| 3 | Llama 3.1 8B Instruct | 77.2 | #4246 |
| 4 | Qwen 3.5 9B | 76.6 | #803 |
| 5 | Mistral Nemo Instruct (2407) | 75.9 | #2947 |
| 6 | EuroLLM-9B-Instruct | 75.2 | #3589 |
| 7 | aya-expanse-8B | 74.5 | #3885 |
| 8 | Mistral 7B Instruct (v0.3) | 73.1 | #6653 |
| 9 | Qwen 3.5 4B | 71.7 | #1175 |
| 10 | Mistral 7B Instruct (v0.2) | 68.3 | #7007 |
| 11 | Llama 3.2 3B Instruct | 61.4 | #7147 |
| 12 | Llama 3.2 1B Instruct | 52.4 | #9047 |
| 13 | Luth-LFM2-1.2B | 51 | #7549 |
| 14 | Lucie-7B | 33.1 | #8468 |
| 15 | Mistral-7B-v0.1 | 24.8 | #6862 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=carte-bretagne · How It Works · Data refreshed daily, snapshot 2026-11-13.