EuroEval French: leaderboard
Metric: Average Score (%). Source: euroeval.com. 383 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 74.38 |
| 2 | Qwen 3 235B A22B 2507 Instruct | 73.2 |
| 3 | Gemma 4 31B (IT) | 73.13 |
| 4 | Claude Sonnet 4.6 | 73.01 |
| 5 | Qwen 3 Next 80B A3B Instruct | 72.45 |
| 6 | Gemini 2.5 Pro | 72.25 |
| 7 | GPT-5 (High) | 72.21 |
| 8 | Llama 3.1 405B Instruct FP8 | 72.14 |
| 9 | Claude Sonnet 4.5 (Thinking) | 71.17 |
| 10 | GPT-5 | 70.97 |
| 11 | Qwen 3 235B A22B | 70.61 |
| 12 | Gemini 3.1 Flash Lite (Preview) | 70.5 |
| 13 | Magistral Small 1.2 | 70.4 |
| 14 | O3 (2025-04-16) | 70.29 |
| 15 | Llama 3.1 405B | 70.19 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-french · How It Works · Data refreshed daily, snapshot 2026-09-05.