EuroEval Bulgarian NLU - BG NER Bsnlp: leaderboard
The "BG NER Bsnlp" subtask of EuroEval Bulgarian NLU. Bulgarian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Micro F1 excluding MISC (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 212 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.20 Beta (0309) (Reasoning) | 93.5 | #204 (Grok 4.20 Beta (0309)) |
| 2 | GPT-5.4 Mini (2026-03-17) (High) | 92.54 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 3 | Claude Sonnet 4.5 (Thinking) | 92.14 | #142 (Claude Sonnet 4.5) |
| 4 | GPT-5 | 91.85 | #98 |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 91.74 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 90.84 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Gemma 4 31B (IT) | 90.62 | #176 |
| 8 | GPT-5 Nano | 90.26 | #425 |
| 9 | Gemini 2.5 Flash (Thinking) | 89.73 | #245 (Gemini 2.5 Flash) |
| 10 | Qwen 3.5 27B FP8 | 88.51 | #164 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 87.68 | #194 |
| 12 | Gemma 4 26B A4B (IT) | 87.64 | #297 |
| 13 | Gemini 2.5 Pro | 87.16 | #152 |
| 14 | Grok 4.1 Fast (Reasoning) | 86.89 | #217 (Grok 4.1 Fast) |
| 15 | Qwen 3.5 35B A3B Base | 86.76 | #310 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bulgarian-nlu-bg-ner-bsnlp · How It Works · Data refreshed daily, snapshot 2026-10-20.