EuroEval Danish NLU - Angry Tweets — leaderboard
Metric: Sentiment classification Score (%). Source: euroeval.com. 436 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 64.26 |
| 2 | Gemini 2.5 Flash (Preview 04-17) | 63.76 |
| 3 | Gemma 4 31B (IT) | 63.59 |
| 4 | Claude Sonnet 4.5 (Non-reasoning) | 62.64 |
| 5 | O3 Mini (2025-01-31) | 62.16 |
| 6 | GLM-4.7 FP8 | 61.64 |
| 7 | Llama 3.1 405B Instruct FP8 | 60.84 |
| 8 | Gemini 3 Pro (Preview) | 60.17 |
| 9 | OLMo 3.1 32B (Thinking) | 59.97 |
| 10 | Gemini 1.5 Pro (002) | 59.25 |
| 11 | Mistral Small 3.1 | 59.08 |
| 12 | GPT-5 | 58.79 |
| 13 | Gemini 3 Flash (Preview) (Non-reasoning) | 58.72 |
| 14 | GPT-5.2 | 58.52 |
| 15 | GLM-4.7 Flash | 58.48 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-danish-nlu-angry-tweets · How the rankings work · Data refreshed daily, snapshot 2026-07-22.