EuroEval Bulgarian NLU - BG NER Bsnlp — leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 212 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.20 Beta (0309) (Reasoning) | 93.5 |
| 2 | GPT-5.4 Mini (High) | 92.54 |
| 3 | GPT-5.4 Mini (Medium) | 92.21 |
| 4 | Claude Sonnet 4.5 (Thinking) | 92.14 |
| 5 | GPT-5 | 91.85 |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 90.84 |
| 7 | Gemma 4 31B (IT) | 90.62 |
| 8 | GPT-5 Nano | 90.26 |
| 9 | Gemini 2.5 Flash (Thinking) | 89.73 |
| 10 | Gemini 3.1 Flash Lite (Preview) | 87.68 |
| 11 | Gemma 4 26B A4B (IT) | 87.64 |
| 12 | Gemini 2.5 Pro | 87.16 |
| 13 | Grok 4.1 Fast (Reasoning) | 86.89 |
| 14 | Claude Sonnet 4.5 (Non-reasoning) | 86.56 |
| 15 | Gemini 3 Pro (Preview) | 86.25 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bulgarian-nlu-bg-ner-bsnlp · How the rankings work · Data refreshed daily, snapshot 2026-07-22.