EuroEval Greek Knowledge: leaderboard
Metric: Knowledge Average Score (%). Source: euroeval.com. 187 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 91.95 |
| 2 | GPT-5 | 91.76 |
| 3 | Claude Sonnet 4.5 (Thinking) | 88.95 |
| 4 | Grok 4.1 Fast (Reasoning) | 88.34 |
| 5 | GPT-5.4 Mini (Medium) | 88.26 |
| 6 | Gemini 2.5 Pro | 87.82 |
| 7 | GPT-5.4 Mini (High) | 87.78 |
| 8 | GPT-5 Mini | 87.01 |
| 9 | Gemini 2.5 Flash (Thinking) | 86.27 |
| 10 | GPT-5.4 Nano (High) | 84.83 |
| 11 | GPT-5 Nano | 83.76 |
| 12 | GPT-5.4 Nano (Medium) | 83.47 |
| 13 | Gemini 3.1 Flash Lite (Preview) | 79 |
| 14 | Qwen 3.5 9B | 78.13 |
| 15 | GPT-5.2 | 77.49 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-knowledge · How It Works · Data refreshed daily, snapshot 2026-09-05.