French LLM Leaderboard - IFEval FR: leaderboard
French IFEval instruction-following score, measuring adherence to constrained French-language prompts.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 55 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.3 70B Instruct | 74.51 | #534 |
| 2 | Qwen 2.5 72B Instruct | 71.1 | #454 |
| 3 | Mistral Large 2 (Nov) Instruct (2411) | 67.44 | #465 |
| 4 | calme-3.2-instruct-78B | 66.84 | #347 |
| 5 | Qwen 2.5 14B Instruct | 66.42 | #647 |
| 6 | DeepSeek R1 Distill Llama 70B | 66.17 | #594 |
| 7 | Falcon3-10B-Instruct | 63.8 | #1157 |
| 8 | Falcon3-7B-Instruct | 62.33 | #1305 |
| 9 | DeepSeek R1 Distill Qwen 32B | 60.14 | #655 |
| 10 | Mixtral 8x22B Instruct (v0.1) | 55.52 | #756 |
| 11 | Mistral Small 3 | 55.34 | #627 |
| 12 | Phi-4 | 52.78 | #706 |
| 13 | Phi-3.5-MoE-instruct | 51.57 | #700 |
| 14 | EuroLLM-9B-Instruct | 46.8 | #1054 |
| 15 | Phi-3-medium-128k-instruct | 46.13 | #1013 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=french-llm-leaderboard-ifeval-fr · How It Works · Data refreshed daily, snapshot 2026-10-20.