EuroEval Finnish NLU - ScaLA FI: leaderboard
Metric: Linguistic acceptability Score (%). Source: euroeval.com. 372 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 62.11 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 59.08 |
| 3 | Gemma 4 31B (IT) | 58.36 |
| 4 | Gemini 2.5 Pro | 53.35 |
| 5 | GPT-5.4 Nano (High) | 51.4 |
| 6 | GPT-5 (Minimal) | 48.36 |
| 7 | GPT-5 (High) | 48.12 |
| 8 | Gemini 2.5 Flash (Preview 04-17) | 47.25 |
| 9 | O3 (2025-04-16) | 46.79 |
| 10 | GPT-5 | 46.59 |
| 11 | Qwen 3 235B A22B 2507 Instruct | 45.86 |
| 12 | Gemma 4 26B A4B (IT) | 45.41 |
| 13 | GPT-4.1 Mini | 45.18 |
| 14 | Gemini 2.5 Flash (Thinking) | 44.49 |
| 15 | Claude 3.5 Sonnet (20241022) | 44.19 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-finnish-nlu-scala-fi · How It Works · Data refreshed daily, snapshot 2026-09-05.