EuroEval Bosnian NLU: leaderboard
Bosnian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: NLU Average Score (%). Source: euroeval.com. Saturation forecast: Around March 2027. 218 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ministral-3-14B-Reasoning-2512 | 66 | #540 |
| 2 | Gemma 4 31B (IT) | 65.47 | #176 |
| 3 | Claude Sonnet 4.5 (Thinking) | 64.64 | #142 (Claude Sonnet 4.5) |
| 4 | Gemini 3 Pro (Preview) | 64.39 | #66 |
| 5 | Mistral Small 3.2 | 64.34 | #605 |
| 6 | Gemini 3 Flash (Preview) (Thinking) | 64.21 | #82 (Gemini 3 Flash (Preview)) |
| 7 | GPT-4.1 Mini | 63.93 | #355 |
| 8 | Gemini 3.1 Pro (Preview) | 63.86 | #58 |
| 9 | Gemini 2.5 Pro | 63.79 | #152 |
| 10 | GPT-5 | 63.74 | #98 |
| 11 | Gemini 2.5 Flash (Thinking) | 63.74 | #245 (Gemini 2.5 Flash) |
| 12 | Bielik-11B-v2.3-Instruct | 63.72 | #693 |
| 13 | GPT-5.2 | 63.61 | #110 |
| 14 | Ministral-3-14B-Instruct-2512 | 63.47 | #615 |
| 15 | Gemma 4 26B A4B (IT) | 63.21 | #297 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bosnian-nlu · How It Works · Data refreshed daily, snapshot 2026-10-20.