EuroEval Icelandic NLU - MIM-GOLD NER: leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 392 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 86.91 |
| 2 | GPT-5 (High) | 85.47 |
| 3 | GPT-5 | 84.43 |
| 4 | GPT-5.4 Mini (High) | 84.04 |
| 5 | GPT-5.4 Mini (Medium) | 83.64 |
| 6 | Gemma 4 31B (IT) | 79.94 |
| 7 | O3 (2025-04-16) | 78.07 |
| 8 | Gemma 4 26B A4B (IT) | 75.89 |
| 9 | Gemini 3 Pro (Preview) | 75.87 |
| 10 | Qwen 3 Next 80B A3B (Thinking) | 75.24 |
| 11 | Gemini 2.5 Flash (Thinking) | 74.9 |
| 12 | Gemini 3.1 Flash Lite (Preview) | 74.85 |
| 13 | Llama 3.1 70B | 73.34 |
| 14 | O4 Mini (2025-04-16) | 72.86 |
| 15 | Gemini 2.5 Flash (Preview 04-17) | 72.59 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-icelandic-nlu-mim-gold-ner · How It Works · Data refreshed daily, snapshot 2026-09-05.