EuroEval Ukrainian NLU - NER UK: leaderboard
The "NER UK" subtask of EuroEval Ukrainian NLU. Ukrainian-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: Around January 2027. 201 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 Mini (2026-03-17) (High) | 83.05 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 2 | GPT-5 | 81.68 | #98 |
| 3 | Claude Sonnet 4.5 (Thinking) | 80.64 | #142 (Claude Sonnet 4.5) |
| 4 | Qwen 3 4B 2507 (Thinking) | 79.05 | #538 (Qwen 3 4B 2507) |
| 5 | Gemma 4 31B (IT) | 76.41 | #176 |
| 6 | Gemini 2.5 Pro | 75.7 | #152 |
| 7 | Gemma 4 26B A4B (IT) | 73.19 | #297 |
| 8 | Qwen 3.5 35B A3B Base | 72.38 | #310 |
| 9 | GPT-5 Nano | 72.35 | #425 |
| 10 | Llama 3.3 70B Instruct | 71.16 | #534 |
| 11 | Gemini 3 Pro (Preview) | 70.98 | #66 |
| 12 | Llama 3.1 70B | 70.25 | #592 |
| 13 | Gemini 3 Flash (Preview) (Non-reasoning) | 70.2 | #82 (Gemini 3 Flash (Preview)) |
| 14 | Voxtral-Small-24B-2507 | 69.76 | #581 |
| 15 | Grok 4.1 Fast (Reasoning) | 68.85 | #217 (Grok 4.1 Fast) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-ukrainian-nlu-ner-uk · How It Works · Data refreshed daily, snapshot 2026-10-20.