Emotional Intelligence
Emotional Intelligence (EI) is a measure of "The ability to monitor one’s own and others’ feelings, to discriminate among them, and to use this information to guide one’s thinking and action." (Salovey and Mayer, 1990). EI is further broken down into four branches: perceiving, using, understanding and managing emotions (Mayer & Salovey, 1997). Of particular relevance to language models that operate exclusively in the text modality is emotional understanding (EU). This is defined as the ability to interpret and analyse the language of emotions, to comprehend complex emotional states, and understand how these emotions can influence behaviour and decision-making.
Papers
Showing 26–50 of 77 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | OpenAI gpt-4-0613 | EQ-Bench Score | 62.52 | — | Unverified |
| 2 | migtissera/SynthIA-70B-v1.5 | EQ-Bench Score | 54.83 | — | Unverified |
| 3 | OpenAI gpt-4-0314 | EQ-Bench Score | 53.39 | — | Unverified |
| 4 | Qwen/Qwen-72B-Chat | EQ-Bench Score | 52.44 | — | Unverified |
| 5 | Anthropic Claude2 | EQ-Bench Score | 52.14 | — | Unverified |
| 6 | meta-llama/Llama-2-70b-chat-hf | EQ-Bench Score | 51.56 | — | Unverified |
| 7 | 01-ai/Yi-34B-Chat | EQ-Bench Score | 51.03 | — | Unverified |
| 8 | OpenAI gpt-3.5-0613 | EQ-Bench Score | 49.17 | — | Unverified |
| 9 | OpenAI gpt-3.5-turbo-0301 | EQ-Bench Score | 47.61 | — | Unverified |
| 10 | Open-Orca/Mistral-7B-OpenOrca | EQ-Bench Score | 44.4 | — | Unverified |