EuroEval Estonian NLU - Grammar ET: leaderboard
Metric: Linguistic acceptability Score (%). Source: euroeval.com. 250 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 62.63 |
| 2 | Gemini 2.5 Pro | 61.06 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 58.7 |
| 4 | Gemini 2.5 Flash (Thinking) | 56 |
| 5 | GPT-5 | 55.2 |
| 6 | GPT-5.4 Mini (High) | 53.72 |
| 7 | Claude Sonnet 4.6 | 52.96 |
| 8 | GPT-4.1 | 52.89 |
| 9 | GPT-5.4 Mini (Medium) | 49.33 |
| 10 | GPT-5.4 Nano (Medium) | 48.69 |
| 11 | GPT-5.2 | 46.89 |
| 12 | GPT-5 Mini | 46.35 |
| 13 | Gemma 3 27B (IT) | 44.41 |
| 14 | Gemma 4 31B (IT) | 42.69 |
| 15 | Qwen 3 235B A22B 2507 Instruct | 41.93 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-estonian-nlu-grammar-et · How It Works · Data refreshed daily, snapshot 2026-09-05.