EuroEval Bulgarian Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 195 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 79.86 |
| 2 | Gemini 3 Pro (Preview) | 76.99 |
| 3 | Grok 4.20 Beta (0309) (Reasoning) | 76.13 |
| 4 | GPT-5 | 75.09 |
| 5 | GPT-5 Mini | 73.26 |
| 6 | Gemini 2.5 Pro | 70.35 |
| 7 | Claude Sonnet 4.5 (Non-reasoning) | 67.42 |
| 8 | Qwen 3.5 9B | 65.77 |
| 9 | Claude Sonnet 4.6 | 64.17 |
| 10 | Gemma 4 31B (IT) | 62.43 |
| 11 | Gemini 2.5 Flash (Thinking) | 60.5 |
| 12 | Grok 4.1 Fast (Reasoning) | 58.06 |
| 13 | Qwen 3.5 4B | 56.57 |
| 14 | GPT-5.4 Mini (High) | 55.91 |
| 15 | Gemini 3.1 Flash Lite (Preview) | 55.74 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-bulgarian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.