EuroEval Greek Common Sense Reasoning: leaderboard
EuroEval's Greek common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Greek, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 187 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 81.52 | #66 |
| 2 | Claude Sonnet 4.5 (Thinking) | 80.87 | #142 (Claude Sonnet 4.5) |
| 3 | Gemini 3 Flash (Preview) (Thinking) | 79.37 | #82 (Gemini 3 Flash (Preview)) |
| 4 | Gemini 3 Flash (Preview) (Non-reasoning) | 78.35 | #82 (Gemini 3 Flash (Preview)) |
| 5 | GPT-5 | 75.57 | #98 |
| 6 | Gemini 2.5 Pro | 72.39 | #152 |
| 7 | GPT-5 Mini (2025-08-07) | 69.09 | #172 |
| 8 | Gemini 2.5 Flash (Thinking) | 67.48 | #245 (Gemini 2.5 Flash) |
| 9 | Claude Sonnet 4.5 (Non-reasoning) | 66.68 | #142 (Claude Sonnet 4.5) |
| 10 | GPT-4.1 | 62.95 | #248 |
| 11 | Grok 4.1 Fast (Reasoning) | 62.73 | #217 (Grok 4.1 Fast) |
| 12 | Gemma 4 31B (IT) | 62.29 | #176 |
| 13 | Qwen 3.5 9B | 60.8 | #379 |
| 14 | GPT-5.4 Mini (2026-03-17) (High) | 60.04 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 15 | Claude Sonnet 4.6 | 56.2 | #90 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.