CARTE - Nouvelle-Aquitaine: 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 180 questions about the Nouvelle-Aquitaine region; higher is better.
Metric: Accuracy (%) on the 180 CARTE questions about Nouvelle-Aquitaine, 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: Around February 2027. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 92.5 | #164 |
| 2 | Mistral Nemo Instruct (2407) | 67.8 | #2947 |
| 3 | Qwen 3.5 9B | 66.1 | #803 |
| 4 | Gemma 3 12B (IT) | 65 | #1837 |
| 5 | Llama 3.1 8B Instruct | 64.4 | #4246 |
| 6 | Qwen 3.5 4B | 61.7 | #1175 |
| 7 | Mistral 7B Instruct (v0.3) | 59.4 | #6653 |
| 8 | EuroLLM-9B-Instruct | 59.4 | #3589 |
| 9 | aya-expanse-8B | 58.3 | #3885 |
| 10 | Mistral 7B Instruct (v0.2) | 53.9 | #7007 |
| 11 | Llama 3.2 3B Instruct | 52.2 | #7147 |
| 12 | Llama 3.2 1B Instruct | 44.4 | #9047 |
| 13 | Luth-LFM2-1.2B | 42.8 | #7549 |
| 14 | Lucie-7B | 40.6 | #8468 |
| 15 | Mistral-7B-v0.1 | 28.3 | #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-nouvelle-aquitaine · How It Works · Data refreshed daily, snapshot 2026-11-13.