Emotional Intelligence On Emotional

평가 지표

EQ-Bench Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	EQ-Bench Score	Paper Title
OpenAI gpt-3.5-0613	49.17	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
lmsys/vicuna-33b-v1.3	36.52	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
lmsys/vicuna-13b-v1.1	32.85	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI text-davinci-002	39.44	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI text-davinci-003	43.73	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
meta-llama/Llama-2-70b-chat-hf	51.56	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI ADA	2.25	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
meta-llama/Llama-2-7b-chat-hf	25.43	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI gpt-3.5-turbo-0301	47.61	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
Intel/neural-chat-7b-v3-1	43.61	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
Qwen/Qwen-72B-Chat	52.44	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
openchat/openchat 3.5	37.08	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
migtissera/SynthIA-70B-v1.5	54.83	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
Open-Orca/Mistral-7B-OpenOrca	44.40	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI gpt-4-0613	62.52	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI gpt-4-0314	53.39	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
Qwen/Qwen-14B-Chat	43.76	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
Koala 13B	24.92	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
meta-llama/Llama-2-13b-chat-hf	33.02	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
OpenAI ADA	2.25	EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models

0 of 24 row(s) selected.