Add Feature Requests Form && Price Table Sort.
update time:2024-8-6 18:20
explore the best
LLM Score
update time: 2024-8-4 23:50 UTC+8
LLM Eval3
| Access Method | Evaluation Date | Relative Score - GPT4 Turbo | Relative Score - GPT3.5 | Absolute Score | Edit | |
|---|---|---|---|---|---|---|
GPT4 Turbo(gpt-4-1106-preview) OpenAI | API | 2023.11.18 | 100 | 141.81 | 73.6 | |
gpt-4-0125-preview OpenAI | API | 2024.1.28 | 97.28 | 137.96 | 71.6 | |
Baidu4.0 百度 | API | 2023.11.1 | 95.56 | 135.52 | 70.33 | |
Yi-34B-Chat 零一万物 | API | 2023.12.1 | 89.27 | 126.59 | 65.7 | |
Baidu3.5 百度 | API | 2023.11.1 | 87.95 | 124.73 | 64.73 | |
ChatGLM-pro Tsinghua&Zhipu.AI | API | 2023.11.1 | 87.95 | 124.73 | 64.73 | |
gpt4-0613 OpenAI | API | 2023.9.29 | 84.19 | 119.4 | 61.97 | |
讯飞星火大模型v3.0 科大讯飞 | API | 2023.11.7 | 83.51 | 118.43 | 61.47 | |
Nanbeige-plus(2) NanBeiGe LLM Lab | API | 2023.12.1 | 86.68 | 117.47 | 61 | |
Baichuan2-13B-Chat Baichuan | Weight | 2023.9.29 | 74.18 | 105.2 | 54.6 | |
Gemini Pro Google | API | 2024.1.10 | 74.05 | 104.95 | 54.5 | |
Qwen-plus Alibaba Cloud | API | 2023.11.1 | 72.01 | 102.12 | 53 | |
Qwen-turbo Alibaba Cloud | API | 2023.11.1 | 70.97 | 100.64 | 52.23 | |
Nanbeige-16B NanBeiGe LLM Lab | API | 2023.10.23 | 70.56 | 100.06 | 51.93 | |
GPT-3.5-turbo OpenAI | API | 2023.9.29 | 70.52 | 100 | 51.9 | |
minimax-abab5 minimax | Weight | 2023.11.1 | 70.43 | 99.87 | 51.83 | |
Mixtral--8x7B-Instruct Mistral AI | Weight | 2024.1.10 | 65.76 | 93.26 | 48.4 | |
ChatGLM2-6B Tsinghua&Zhipu.AI | Weight | 2023.9.29 | 53.85 | 76.36 | 39.63 | |
ziya_v1.1-13b IDEA研究院 | Weight | 2023.9.29 | 51.13 | 72.51 | 37.63 | |
InternLM-Chat-7B Shanghai AI Laboratory&Sense Time | Weight | 2023.9.29 | 49.28 | 69.88 | 36.27 | |
Linly-Chinese-LLaMA-2-13B-hf 大数据系统计算技术国家工程实验室 | Weight | 2023.10.3 | 47.15 | 66.86 | 34.7 | |
BELLE-Llama2-13B-chat-0.4M LianjiaTech | Weight | 2023.10.1 | 46.15 | 65.45 | 33.97 | |
Llama-2-7b-chat-hf Meta | Weight | 2023.9.29 | 32.11 | 45.54 | 23.63 |
