EuroEval French NLU - Allocine: leaderboard
Metric: Sentiment classification Score (%). Source: euroeval.com. 377 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 (2025-04-16) | 98.19 |
| 2 | Ministral 3 14B | 97.8 |
| 3 | GPT-5 (High) | 97.33 |
| 4 | GPT-5 | 97.1 |
| 5 | GPT-5 (Minimal) | 97.1 |
| 6 | Ministral-3-14B-Instruct-2512 | 96.93 |
| 7 | Grok 4.1 Fast (Reasoning) | 96.79 |
| 8 | GPT-5.4 Mini (High) | 96.79 |
| 9 | Gemini 3 Pro (Preview) | 96.7 |
| 10 | Ministral-3-8B-Instruct-2512 | 96.63 |
| 11 | Ministral 3 8B | 96.58 |
| 12 | Grok 3 | 96.47 |
| 13 | GPT-5 Nano (High) | 96.47 |
| 14 | Gemma 4 31B (IT) | 96.46 |
| 15 | Claude Sonnet 4.6 | 96.31 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-french-nlu-allocine · How It Works · Data refreshed daily, snapshot 2026-09-05.