EuroEval Bosnian: leaderboard
Bosnian-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Around February 2027. 218 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 Mini | 63.93 | #355 |
| 2 | Gemini 3.1 Pro (Preview) | 63.86 | #58 |
| 3 | Gemini 2.5 Pro | 63.79 | #152 |
| 4 | GPT-5 | 63.74 | #98 |
| 5 | Gemini 2.5 Flash (Thinking) | 63.74 | #245 (Gemini 2.5 Flash) |
| 6 | Gemini 2.5 Flash (Non-reasoning) | 62.35 | #245 (Gemini 2.5 Flash) |
| 7 | Bielik-11B-v2.3-Instruct | 58.74 | #693 |
| 8 | Granite 4.0 H Small | 57.76 | #665 |
| 9 | GPT-4.1 Nano | 56.05 | #731 |
| 10 | Mistral Small 3.2 | 56.03 | #605 |
| 11 | Claude Sonnet 4.5 (Thinking) | 55.5 | #142 (Claude Sonnet 4.5) |
| 12 | Gemini 3 Pro (Preview) | 55.45 | #66 |
| 13 | OLMo 3.1 32B (Thinking) | 55.41 | #632 (OLMo 3.1 32B) |
| 14 | Claude Sonnet 4.5 (Non-reasoning) | 54.95 | #142 (Claude Sonnet 4.5) |
| 15 | Gemini 2.5 Flash Lite (Non-reasoning) | 54.64 | #422 (Gemini 2.5 Flash Lite) |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.