EuroEval Bulgarian Knowledge — leaderboard
Metric: Knowledge Average Score (%). Source: euroeval.com. 195 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Non-reasoning) | 80.16 |
| 2 | Gemini 3 Pro (Preview) | 78.76 |
| 3 | GPT-5 | 78.29 |
| 4 | GPT-5.4 Mini (High) | 78.05 |
| 5 | Gemini 2.5 Pro | 76.88 |
| 6 | Gemini 3.1 Flash Lite (Preview) | 76.88 |
| 7 | GPT-5.4 Mini (Medium) | 76.32 |
| 8 | Gemini 2.5 Flash (Thinking) | 76.32 |
| 9 | Grok 4.20 Beta (0309) (Reasoning) | 76.32 |
| 10 | Claude Sonnet 4.6 | 75.2 |
| 11 | Gemini 2.5 Flash Lite (Thinking) | 75 |
| 12 | GPT-5.2 | 71.84 |
| 13 | GPT-4.1 | 71.39 |
| 14 | GPT-5.4 Mini (Non-reasoning) | 71.31 |
| 15 | Grok 4.1 Fast (Reasoning) | 70.17 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bulgarian-knowledge · How the rankings work · Data refreshed daily, snapshot 2026-07-22.