Evals for Every Language - Finnish (fi): leaderboard
Average score across evaluation tasks in Finnish (fi), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78.29 | #58 |
| 2 | Claude Opus 4.8 | 77.18 | #37 |
| 3 | Claude Sonnet 4.6 | 76.97 | #90 |
| 4 | Qwen 3.6 Plus | 76.48 | #120 |
| 5 | Claude Sonnet 4.5 | 75.15 | #142 |
| 6 | Llama 4 Maverick | 74.76 | #464 |
| 7 | Claude Sonnet 4 | 74.11 | #199 |
| 8 | Claude Opus 4.7 | 74.04 | #49 |
| 9 | GPT-5.1 | 72.83 | #135 |
| 10 | Gemini 2.5 Pro | 72.61 | #152 |
| 11 | Gemini 3.1 Flash Lite | 72.42 | #191 |
| 12 | GPT-5 | 72.09 | #98 |
| 13 | GPT-5.3 | 71.73 | #103 |
| 14 | Llama 3.1 70B Instruct | 71.46 | #561 |
| 15 | Qwen 3 30B A3B 2507 Instruct | 71.39 | #488 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-fi · How It Works · Data refreshed daily, snapshot 2026-10-20.