Unverified50% confidenceFactExact time
Common sub-benchmarks included in composite intelligence indices are MMLU, HumanEval, MBPP, MATH, GSM8K, GPQA, and LongBench.
1
Sources
50%
Confidence
Long-term
Relevance
9/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSpec配套九个评测基准，涵盖数学推理（GSM8K、MATH-500）、代码生成（HumanEval、MBPP、LiveCodeBench）和通用对话（MT-Bench、Alpaca、Arena-Hard v2）74% similarUnverifiedIn domestic mainstream large model programming capability tests, Zhipu GLM ranks first, while DeepSeek, Kimi, and MiniMax are in the second tier, and Alibaba Tongyi and Tencent Hunyuan perform slightly worse.64% similarUnverifiedThe tutorial recommends four mainstream models: Llama 3.1 (Meta) for the strongest overall capability, DeepSeek R1 (DeepSeek) for deep reasoning, Qwen 3 (Alibaba Tongyi Qianwen) for the best Chinese language performance, and Gemma 3 (Google) for multimodal support.63% similarUnverifiedGoogle DeepMind proposed a six-level classification framework for AGI, ranging from Level 0 to Level 5 (superhuman); the most advanced current large models are roughly situated in the Level 1 to Level 2 general range.62% similarUnverifiedMulti-Token Prediction (MTP) technology has been adopted by DeepSeek, Meta, and Google, and is becoming a standard capability of large models.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/941568API
curl https://kongchang.com/api/v1/knowledge/claims/941568MCP
get_claim(id=941568)