EuroEval Albanian Common Sense Reasoning: leaderboard
EuroEval's Albanian common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Albanian, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 183 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 85.24 | #58 |
| 2 | Gemini 3 Pro (Preview) | 82.09 | #66 |
| 3 | Gemini 2.5 Flash (Thinking) | 80.03 | #245 (Gemini 2.5 Flash) |
| 4 | Qwen 3.5 27B FP8 | 79.32 | #164 |
| 5 | Gemini 2.5 Pro | 77.16 | #152 |
| 6 | Qwen 3.5 35B A3B FP8 | 76.62 | #362 |
| 7 | GPT-5 | 76.25 | #98 |
| 8 | Gemini 3 Flash (Preview) (Thinking) | 75.4 | #82 (Gemini 3 Flash (Preview)) |
| 9 | Claude Sonnet 4.5 (Thinking) | 73.76 | #142 (Claude Sonnet 4.5) |
| 10 | Gemini 3 Flash (Preview) (Non-reasoning) | 69.33 | #82 (Gemini 3 Flash (Preview)) |
| 11 | GPT-5 Mini (2025-08-07) | 67.69 | #172 |
| 12 | GPT-4.1 | 66.31 | #248 |
| 13 | Grok 4.1 Fast (Reasoning) | 64.77 | #217 (Grok 4.1 Fast) |
| 14 | Grok 4.20 Beta (0309) (Reasoning) | 63.48 | #204 (Grok 4.20 Beta (0309)) |
| 15 | Qwen 3.5 9B | 60.44 | #379 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-albanian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.