| Models,Teaser,AI,Roleplay,Chat,Math,Reasoning,Creation,Code,Science,Humanities,Average,Class | |
| GPT-4o-0806,0.82,0.53,0.62,0.61,0.83,0.67,0.67,0.73,0.64,0.55,0.667,API | |
| Skywork-llama3.1-8B,0.69,0.61,0.54,0.62,0.63,0.64,0.6,0.69,0.74,0.53,0.629,Judge | |
| Qwen2.5-72B-Chat,0.68,0.57,0.57,0.47,0.78,0.64,0.58,0.75,0.61,0.52,0.617,General | |
| CJ-1-32B,0.66,0.57,0.56,0.59,0.78,0.58,0.55,0.75,0.6,0.49,0.613,Judge | |
| CJ-1-14B,0.66,0.51,0.57,0.54,0.72,0.61,0.56,0.74,0.61,0.47,0.599,Judge | |
| Qwen2-72B-Chat,0.63,0.59,0.54,0.49,0.62,0.64,0.6,0.74,0.51,0.52,0.588,General | |
| CJ-1-7B,0.56,0.56,0.51,0.47,0.68,0.58,0.58,0.75,0.58,0.43,0.57,Judge | |
| Qwen2.5-7B-Chat,0.54,0.59,0.59,0.46,0.69,0.43,0.61,0.65,0.58,0.52,0.566,General | |
| CJ-1-1.5B,0.42,0.56,0.56,0.43,0.66,0.47,0.55,0.78,0.64,0.44,0.551,Judge | |
| Selftaught-llama3.1-70B,0.47,0.45,0.47,0.37,0.45,0.43,0.36,0.58,0.48,0.36,0.442,Judge | |