EuroEval Estonian NLU - Estonian Valence — leaderboard
Metric: Sentiment classification Score (%). Source: euroeval.com. 251 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite (Preview) | 67.41 |
| 2 | GPT-5 | 65.74 |
| 3 | Gemini 2.5 Pro | 64.76 |
| 4 | Gemma 3 27B (IT) | 64.43 |
| 5 | Qwen 3 235B A22B 2507 Instruct | 64.41 |
| 6 | Claude Sonnet 4.6 | 63.92 |
| 7 | Llama 3.3 70B Instruct | 63.89 |
| 8 | Claude Sonnet 4.5 (Thinking) | 63.49 |
| 9 | Gemini 3 Pro (Preview) | 63.19 |
| 10 | Gemma 3 12B (IT) | 63.17 |
| 11 | Llama 3.1 70B Instruct | 63.07 |
| 12 | GPT-5.2 | 63.06 |
| 13 | Qwen 3 Next 80B A3B Instruct | 63.01 |
| 14 | Gemma 4 26B A4B (IT) | 62.78 |
| 15 | Gemma 4 31B (IT) | 62.19 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-estonian-nlu-estonian-valence · How the rankings work · Data refreshed daily, snapshot 2026-07-22.