EuroEval Ukrainian NLU - MultiWikiQA UK: leaderboard
The "MultiWikiQA 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: Character F1 (%). Source: euroeval.com. Saturation forecast: Around January 2027. 199 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ministral-3-14B-Reasoning-2512 | 71.57 | #540 |
| 2 | gemma-3-27B-pt | 69.97 | #502 |
| 3 | Mistral Small 3.2 | 69.59 | #605 |
| 4 | Llama 3.1 70B | 68.94 | #592 |
| 5 | Qwen 3 14B (Non-reasoning) | 67.41 | #537 (Qwen 3 14B) |
| 6 | gemma-3-12B-pt | 67.1 | #686 |
| 7 | Llama 3.1 8B | 66.87 | #1151 |
| 8 | Qwen3.5-4B-Base | 66.61 | #798 |
| 9 | Voxtral-Small-24B-2507 | 66.13 | #581 |
| 10 | SOLAR-10.7B-v1.0 | 65.14 | #1253 |
| 11 | Gemma 4 31B | 64.71 | #200 |
| 12 | Mistral Small 3.1 | 64.58 | #610 |
| 13 | Qwen 3 32B (Non-reasoning) | 64.15 | #443 (Qwen 3 32B) |
| 14 | Ministral-3-14B-Instruct-2512 | 63.85 | #615 |
| 15 | Qwen 2.5 72B Instruct | 62.75 | #454 |
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-multiwikiqa-uk · How It Works · Data refreshed daily, snapshot 2026-10-20.