CUE-Bench - Fine-grained Emotion: leaderboard
CUE-Bench (Huazhong University of Science and Technology, 2026) evaluates affective understanding of Chinese discourse beyond surface sentiment, using contextual instances across three connected tasks. Accuracy on fine-grained emotion classification under zero-shot direct prompting, in percent, higher is better.
Metric: Accuracy (%; fine-grained emotion classification; over CUE-Bench's Chinese-discourse instances with context; zero-shot direct prompting). Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.1 | 30.5 | #175 |
| 2 | DeepSeek V4 Flash | 24.7 | #254 |
| 3 | Llama 4 Maverick | 23.7 | #1105 |
| 4 | Qwen 3 8B | 20.9 | #1838 |
| 5 | Llama 3.1 8B | 14.2 | #4900 |
| 6 | GPT-4o Mini | 11.5 | #1627 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=cue-bench-fine-grained-emotion · How It Works · Data refreshed daily, snapshot 2026-11-12.