EuroEval Estonian NLU - EstNER — leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 250 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 58.07 |
| 2 | GPT-5.4 Mini (High) | 57.99 |
| 3 | gemma-3-27B-pt | 57.31 |
| 4 | Llama 3.1 70B | 57.15 |
| 5 | Claude Sonnet 4.5 (Thinking) | 56.74 |
| 6 | Magistral Small | 56.59 |
| 7 | GPT-5 | 56.4 |
| 8 | Mistral Small 3.2 | 56.26 |
| 9 | Llama 3.1 70B Instruct | 55.96 |
| 10 | GPT-5.4 Mini (Medium) | 55.82 |
| 11 | Llama 3.3 70B Instruct | 55.71 |
| 12 | GPT-5 Nano | 55.07 |
| 13 | Mistral Small 3.1 | 54.69 |
| 14 | Gemini 3 Pro (Preview) | 54.18 |
| 15 | Qwen 2.5 72B Instruct | 53.88 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-estonian-nlu-estner · How the rankings work · Data refreshed daily, snapshot 2026-07-22.