EuroEval Hungarian NLU - MultiWikiQA HU: leaderboard
The "MultiWikiQA HU" subtask of EuroEval Hungarian NLU. Hungarian-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. 203 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B | 73.61 | #592 |
| 2 | Ministral-3-14B-Reasoning-2512 | 71.83 | #540 |
| 3 | Qwen 3 32B (Non-reasoning) | 70.37 | #443 (Qwen 3 32B) |
| 4 | Mistral Small 3.2 | 69.98 | #605 |
| 5 | gemma-3-27B-pt | 69.94 | #502 |
| 6 | SOLAR-10.7B-v1.0 | 69.79 | #1253 |
| 7 | Qwen 3 14B (Non-reasoning) | 69.66 | #537 (Qwen 3 14B) |
| 8 | Bielik-11B-v2.3-Instruct | 68.38 | #693 |
| 9 | Qwen3.5-4B-Base | 68.25 | #798 |
| 10 | gemma-4-E4B-it | 67.2 | #566 |
| 11 | Gemma 4 31B (IT) | 66.59 | #176 |
| 12 | Gemma 3 27B (IT) | 65.99 | #523 |
| 13 | Gemini 3 Pro (Preview) | 65.7 | #66 |
| 14 | Claude Sonnet 4.5 (Non-reasoning) | 65.69 | #142 (Claude Sonnet 4.5) |
| 15 | Voxtral-Small-24B-2507 | 65.6 | #581 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-hungarian-nlu-multiwikiqa-hu · How It Works · Data refreshed daily, snapshot 2026-10-20.