EuroEval Estonian Knowledge — leaderboard
Metric: Knowledge Average Score (%). Source: euroeval.com. 227 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 53.8 |
| 2 | Gemini 2.5 Pro | 51.82 |
| 3 | Gemini 3 Pro (Preview) | 51.79 |
| 4 | Claude Sonnet 4.5 (Thinking) | 50.17 |
| 5 | GPT-5.4 Mini (High) | 49.28 |
| 6 | Gemini 3.1 Flash Lite (Preview) | 49.15 |
| 7 | GPT-5.4 Mini (Medium) | 47.7 |
| 8 | Gemini 3 Flash (Preview) (Non-reasoning) | 47.01 |
| 9 | Claude Sonnet 4.6 | 39.93 |
| 10 | Gemini 2.5 Flash (Thinking) | 39.55 |
| 11 | GPT-5 Mini | 39.52 |
| 12 | GPT-4.1 | 38.98 |
| 13 | Claude Sonnet 4.5 (Non-reasoning) | 37.27 |
| 14 | Grok 4.1 Fast (Reasoning) | 36.98 |
| 15 | Gemini 2.5 Flash (Non-reasoning) | 35.2 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-estonian-knowledge · How the rankings work · Data refreshed daily, snapshot 2026-07-22.