EuroEval Swedish Knowledge: leaderboard
EuroEval's Swedish knowledge task — multiple-choice general-knowledge questions in Swedish, from the EuroEval European language model benchmark suite.
Metric: Knowledge Average Score (%). Source: euroeval.com. Saturation forecast: Around April 2027. 338 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 Mini (2026-03-17) (High) | 88.01 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 2 | GPT-5 (2025-08-07) (High) | 87.92 | |
| 3 | Claude Sonnet 4.5 (Thinking) | 87.74 | #142 (Claude Sonnet 4.5) |
| 4 | GPT-5 | 87.33 | #98 |
| 5 | Gemini 3 Pro (Preview) | 86.09 | #66 |
| 6 | O3 (2025-04-16) | 85.53 | #121 |
| 7 | Gemini 3 Flash (Preview) (Thinking) | 85.46 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Gemini 2.5 Pro | 85.41 | #152 |
| 9 | Qwen 3 Next 80B A3B (Thinking) | 84.63 | #320 (Qwen 3 Next 80B A3B) |
| 10 | Gemini 3 Flash (Preview) (Non-reasoning) | 84.2 | #82 (Gemini 3 Flash (Preview)) |
| 11 | Gemini 2.5 Pro (Preview 03-25) | 83.44 | #123 |
| 12 | Qwen 3 235B A22B | 83.4 | #313 |
| 13 | GPT-5 Mini (2025-08-07) | 82.29 | #172 |
| 14 | Gemini 3.1 Flash Lite (Preview) | 81.91 | #194 |
| 15 | Gemini 2.5 Flash (Preview 04-17) | 81.43 | #237 |
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-knowledge · How It Works · Data refreshed daily, snapshot 2026-10-20.