| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| EQ-Bench | Gemini-2.5-pro | Overall Score86.4 | 19 | 2mo ago | |
| EIBench Basic 1.0 (test) | CFSA | Happy Score (LLaMA-3)69.68 | 19 | 4mo ago | |
| EIBench (test) | CHARM Score43.8 | 15 | 1mo ago | ||
| EQ-Bench3 | Qwen3-8B + PereGRM@8 | Overall Score83.3 | 12 | 1mo ago | |
| EiCAP-Bench | GPT-5 | Macro Accuracy99.8 | 8 | 1mo ago | |
| EIBench DeepSeek-v4-pro simulator | Qwen3-8B base | Score23.7 | 4 | 1mo ago | |
| EIBench Qwen3-Max simulator | CTC-GRPO 32B | Score28.7 | 4 | 1mo ago | |
| SECEU | Llama3-70B-Instruct | Sentiment Score (CN)2.36 | 4 | 2mo ago | |
| Turing (test) | C-SFT-Empathy | Turing Test Score14.16 | 4 | 2mo ago |
