EuroEval Swedish: leaderboard
Swedish-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. 412 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 (2025-08-07) (High) | 78.64 | |
| 2 | GPT-5 | 76.44 | #98 |
| 3 | Llama 3.1 405B Instruct FP8 | 76.31 | #389 |
| 4 | Gemini 2.5 Pro | 75.64 | #152 |
| 5 | Qwen 3 235B A22B 2507 Instruct | 75.4 | #300 |
| 6 | Claude 3.7 Sonnet (20250219) (Thinking) | 75.15 | #201 (Claude 3.7 Sonnet (20250219)) |
| 7 | Gemini 2.5 Pro (Preview 03-25) | 74.47 | #123 |
| 8 | O3 (2025-04-16) | 74.18 | #121 |
| 9 | Gemini 2.5 Flash (Thinking) | 74.02 | #245 (Gemini 2.5 Flash) |
| 10 | Claude Sonnet 4.5 (Thinking) | 73.79 | #142 (Claude Sonnet 4.5) |
| 11 | Gemini 3 Pro (Preview) | 73.61 | #66 |
| 12 | Llama 3.1 405B | 73.61 | #466 |
| 13 | Qwen 3 Next 80B A3B Instruct | 72.24 | #368 |
| 14 | Qwen 3 235B A22B | 72.08 | #313 |
| 15 | Gemma 4 31B (IT) | 71.84 | #176 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-swedish · How It Works · Data refreshed daily, snapshot 2026-10-20.