AlpsBench - Emotional Intelligence (Chinese): leaderboard
Metric: Emotional-intelligence score (1 to 5) of responses to Chinese user queries, rated by a DeepSeek-V3.2 judge used as a reward model given the dialogue history; AlpsBench's 2,500 human-verified instances per task built from long-term real user-LLM dialogues in WildChat; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V3.2 (Thinking) | 4 | #198 (DeepSeek V3.2) |
| 2 | GPT-5.2 | 3.9 | #105 |
| 3 | Qwen 3 Max | 3.84 | #201 |
| 4 | Gemini 3 Flash (Preview) | 3.58 | #78 |
| 5 | Claude Sonnet 4.5 | 3.05 | #138 |
| 6 | GPT-4.1 Mini | 2.92 | #346 |
| 7 | Llama 4 Maverick | 2.38 | #451 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=alpsbench-emotional-intelligence-chinese · How It Works · Data refreshed daily, snapshot 2026-10-11.