CARTE - Bretagne: leaderboard
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 |
|---|---|---|
| 1 | Gemini 3 Flash | 96.2 |
| 2 | Gemma 3 12B (IT) | 82.1 |
| 3 | Llama 3.1 8B Instruct | 77.2 |
| 4 | Qwen 3.5 9B | 76.6 |
| 5 | Mistral Nemo Instruct (2407) | 75.9 |
| 6 | aya-expanse-8B | 74.5 |
| 7 | Mistral 7B Instruct (v0.3) | 73.1 |
| 8 | Qwen 3.5 4B | 71.7 |
| 9 | Mistral 7B Instruct (v0.2) | 68.3 |
| 10 | Llama 3.2 3B Instruct | 61.4 |
| 11 | Llama 3.2 1B Instruct | 52.4 |
| 12 | Luth-LFM2-1.2B | 51 |
| 13 | Lucie-7B | 33.1 |
| 14 | Mistral-7B-v0.1 | 24.8 |
| 15 | Gaperon-1125-1B-SFT | 22.1 |
Interactive version: theaggregate.ai/benchmark?slug=carte-bretagne · How It Works · Data refreshed daily, snapshot 2026-09-29.