ArxivMath推理

#	模型	得分 (%)	厂商	来源
1	Claude Opus 4.8	71.8	Anthropic	Hy3 Hugging Face README
2	GPT-5.5	71.5	OpenAI	Hy3 Hugging Face README
3	Gemini 3.1 Pro	64.8	Google	Hy3 Hugging Face README
4	DeepSeek-V4-Pro	56.4	深度求索	Hy3 Hugging Face README
5	Qwen3.7-Max	56	阿里巴巴	Hy3 Hugging Face README
6	Seed2.1 Pro	53.4	字节跳动	Hy3 Hugging Face README
7	DeepSeek-V4-Flash	52.6	深度求索	Hy3 Hugging Face README
8	混元3	52.2	腾讯	Hy3 Hugging Face README
9	混元3 Preview	46.1	腾讯	Hy3 Hugging Face README
10	GLM-5.2	44.2	智谱AI	Hy3 Hugging Face README

正在加载基准详情

#	模型	得分 (%)	厂商	来源
1	Claude Opus 4.8	71.8	Anthropic	Hy3 Hugging Face README
2	GPT-5.5	71.5	OpenAI	Hy3 Hugging Face README
3	Gemini 3.1 Pro	64.8	Google	Hy3 Hugging Face README
4	DeepSeek-V4-Pro	56.4	深度求索	Hy3 Hugging Face README
5	Qwen3.7-Max	56	阿里巴巴	Hy3 Hugging Face README
6	Seed2.1 Pro	53.4	字节跳动	Hy3 Hugging Face README
7	DeepSeek-V4-Flash	52.6	深度求索	Hy3 Hugging Face README
8	混元3	52.2	腾讯	Hy3 Hugging Face README
9	混元3 Preview	46.1	腾讯	Hy3 Hugging Face README
10	GLM-5.2	44.2	智谱AI	Hy3 Hugging Face README