EuroEval Finnish: leaderboard
Finnish-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 382 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 (2025-08-07) (High) | 72.92 | |
| 2 | GPT-5 | 71.55 | #98 |
| 3 | Gemini 2.5 Pro | 69.81 | #152 |
| 4 | Gemini 2.5 Flash (Thinking) | 68.93 | #245 (Gemini 2.5 Flash) |
| 5 | Gemini 2.5 Flash (Preview 04-17) | 68.77 | #237 |
| 6 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 68 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 7 | Qwen 3 235B A22B 2507 Instruct | 67.94 | #300 |
| 8 | O3 (2025-04-16) | 67.87 | #121 |
| 9 | Llama 3.1 405B | 67.48 | #466 |
| 10 | Qwen 3.5 35B A3B FP8 | 66.81 | #362 |
| 11 | Gemma 4 31B (IT) | 66.55 | #176 |
| 12 | GPT-5 Mini (2025-08-07) (High) | 66.43 | #172 (GPT-5 Mini (2025-08-07)) |
| 13 | Gemini 3 Pro (Preview) | 65.88 | #66 |
| 14 | Gemini 2.5 Flash (Non-reasoning) | 65.88 | #245 (Gemini 2.5 Flash) |
| 15 | Gemini 3 Flash (Preview) (Thinking) | 65.85 | #82 (Gemini 3 Flash (Preview)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-finnish · How It Works · Data refreshed daily, snapshot 2026-10-20.