EuroEval English NLU - CoNLL EN: leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 333 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 89.97 |
| 2 | GPT-5 (High) | 88.6 |
| 3 | Claude Sonnet 4.5 (Non-reasoning) | 88.59 |
| 4 | Gemma 4 31B (IT) | 88.53 |
| 5 | Gemma 4 26B A4B (IT) | 87.04 |
| 6 | Gemini 3 Pro (Preview) | 86.89 |
| 7 | Qwen 3 Next 80B A3B (Thinking) | 86.82 |
| 8 | O3 (2025-04-16) | 86.49 |
| 9 | Qwen 3 4B 2507 (Thinking) | 86.34 |
| 10 | GPT-5.4 Mini (High) | 85.75 |
| 11 | GPT-5 | 85.59 |
| 12 | GPT-5.4 Mini (Medium) | 85.19 |
| 13 | Qwen 3 235B A22B | 84.93 |
| 14 | Grok 4.1 Fast (Reasoning) | 84.82 |
| 15 | OLMo 3.1 32B (Thinking) | 84.82 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-english-nlu-conll-en · How It Works · Data refreshed daily, snapshot 2026-09-05.