EuroEval Bulgarian NLU - MultiWikiQA BG — leaderboard
Metric: Reading comprehension Score (%). Source: euroeval.com. 212 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Ministral-3-14B-Reasoning-2512 | 80.66 |
| 2 | Mistral Small 3.2 | 79.74 |
| 3 | Ministral 3 14B | 79.67 |
| 4 | SOLAR-10.7B-v1.0 | 79.17 |
| 5 | gemma-3-27B-pt | 78.42 |
| 6 | gemma-3-12B-pt | 77.91 |
| 7 | Llama 3.1 70B | 77.58 |
| 8 | Ministral 3 8B | 77.13 |
| 9 | Qwen 3 14B (Non-reasoning) | 77.08 |
| 10 | Mistral Small 3.1 | 76.8 |
| 11 | Ministral 3 3B | 76.1 |
| 12 | Ministral-3-14B-Instruct-2512 | 75.41 |
| 13 | Llama 3.1 8B | 74.41 |
| 14 | Tiny Aya Global | 73.92 |
| 15 | gemma-3-4B-pt Base | 73.32 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bulgarian-nlu-multiwikiqa-bg · How the rankings work · Data refreshed daily, snapshot 2026-07-22.