EuroEval French: leaderboard
French-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 383 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 74.38 | #66 |
| 2 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 73.27 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 3 | Qwen 3 235B A22B 2507 Instruct | 73.2 | #300 |
| 4 | Gemma 4 31B (IT) | 73.13 | #176 |
| 5 | Claude Sonnet 4.6 | 73.01 | #90 |
| 6 | Qwen 3 Next 80B A3B Instruct | 72.45 | #368 |
| 7 | Gemini 3 Flash (Preview) (Non-reasoning) | 72.3 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Gemini 3 Flash (Preview) (Thinking) | 72.26 | #82 (Gemini 3 Flash (Preview)) |
| 9 | Gemini 2.5 Pro | 72.25 | #152 |
| 10 | GPT-5 (2025-08-07) (High) | 72.21 | |
| 11 | Llama 3.1 405B Instruct FP8 | 72.14 | #389 |
| 12 | Claude Sonnet 4.5 (Thinking) | 71.17 | #142 (Claude Sonnet 4.5) |
| 13 | GPT-5 | 70.97 | #98 |
| 14 | Qwen 3 235B A22B | 70.61 | #313 |
| 15 | Gemini 3.1 Flash Lite (Preview) | 70.5 | #194 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-french · How It Works · Data refreshed daily, snapshot 2026-10-20.