EuroEval Greek NLU - ELNER: leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 204 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 81.13 |
| 2 | GPT-5 Nano | 80.71 |
| 3 | GPT-5.4 Mini (High) | 80.26 |
| 4 | GPT-5.4 Mini (Medium) | 79.92 |
| 5 | Claude Sonnet 4.6 | 79.63 |
| 6 | Gemini 3.1 Flash Lite (Preview) | 78.88 |
| 7 | Gemma 4 31B (IT) | 77.95 |
| 8 | Gemini 3 Pro (Preview) | 77.21 |
| 9 | Gemma 4 26B A4B (IT) | 75.82 |
| 10 | GPT-5 | 74.59 |
| 11 | Llama 3.3 70B Instruct | 74.21 |
| 12 | Grok 4.1 Fast (Reasoning) | 72.87 |
| 13 | Gemini 2.5 Pro | 72.71 |
| 14 | Mistral Small 3.2 | 72.57 |
| 15 | Gemini 2.5 Flash (Thinking) | 72.51 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-nlu-elner · How It Works · Data refreshed daily, snapshot 2026-09-05.