EuroEval Albanian Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 183 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 85.24 |
| 2 | Gemini 3 Pro (Preview) | 82.09 |
| 3 | Gemini 2.5 Flash (Thinking) | 80.03 |
| 4 | Gemini 2.5 Pro | 77.16 |
| 5 | GPT-5 | 76.25 |
| 6 | Claude Sonnet 4.5 (Thinking) | 73.76 |
| 7 | GPT-5 Mini | 67.69 |
| 8 | GPT-4.1 | 66.31 |
| 9 | Grok 4.1 Fast (Reasoning) | 64.77 |
| 10 | Grok 4.20 Beta (0309) (Reasoning) | 63.48 |
| 11 | Qwen 3.5 9B | 60.44 |
| 12 | Gemma 4 31B (IT) | 60.3 |
| 13 | Gemini 3.1 Flash Lite (Preview) | 56.89 |
| 14 | Claude Sonnet 4.6 | 52.05 |
| 15 | Claude Sonnet 4.5 (Non-reasoning) | 51.97 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-albanian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.