EuroEval German Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 310 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 92.63 |
| 2 | Claude Sonnet 4.5 (Thinking) | 90.85 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 86.72 |
| 4 | Mistral Small 3.1 | 84.1 |
| 5 | Llama 3.1 405B Instruct FP8 | 82.81 |
| 6 | Claude Sonnet 4.6 | 82.68 |
| 7 | Gemini 3 Pro (Preview) | 82.16 |
| 8 | GPT-5 (Minimal) | 82.15 |
| 9 | Mistral Small 3 | 82.04 |
| 10 | Qwen 3 Next 80B A3B Instruct | 81.74 |
| 11 | GPT-5 (High) | 81.13 |
| 12 | Gemini 2.5 Pro | 81.11 |
| 13 | GPT-5 | 79.73 |
| 14 | GPT-4.1 | 79.65 |
| 15 | Claude 3.7 Sonnet (20250219) (Thinking) | 79.4 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-german-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.