EuroEval English NLU: leaderboard
Metric: NLU Average Score (%). Source: euroeval.com. 341 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 77.22 |
| 2 | Claude Sonnet 4.6 | 77.12 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 76.79 |
| 4 | GPT-5.4 Mini (Medium) | 76.66 |
| 5 | Gemini 3 Pro (Preview) | 76.03 |
| 6 | Grok 4.1 Fast (Reasoning) | 75.92 |
| 7 | Gemma 4 26B A4B (IT) | 75.35 |
| 8 | GPT-5.4 Mini (High) | 75.28 |
| 9 | Llama 3.1 70B | 75.12 |
| 10 | Llama 3.1 405B | 74.19 |
| 11 | GLM-4.7 Flash | 73.87 |
| 12 | GPT-5.2 | 73.82 |
| 13 | Claude Sonnet 4.5 (Thinking) | 73.48 |
| 14 | Claude Sonnet 4.5 (Non-reasoning) | 73.36 |
| 15 | Ministral-3-14B-Reasoning-2512 | 73.2 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-english-nlu · How It Works · Data refreshed daily, snapshot 2026-09-05.