Unverified50% confidenceBenchmarkExact time
在一道三样本数学题上，DeepSeek V4.1 Flash达到74分，与Opus 5.0持平，超过GLM的67分和V4 Pro的62分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedV4.1 Flash提供低、中、最高三档推理强度，八项推理基准平均分从67.1涨到76.3，代价是输出Token增加约2.5倍78% similarUnverifiedV4.1-Flash在某编程测试维度的得分达到74.2分，相比V4-Flash提升了将近20分76% similarUnverified官方表示HY3在大部分场景中优于参数规模相当的Deepseek V4 Flash，并在内部盲测中平均得分高于GLM系列模型74% similarUnverified在综合智能指数AA上，Qwen3.8 Flash Next得分56，Qwen3.8 Flash云端版得分57，DeepSeek V4 Flash得分5274% similarUnverifiedV4 Pro的参数量是Flash模型的近6倍，但实际表现未能拉开显著差距72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924488API
curl https://kongchang.com/api/v1/knowledge/claims/924488MCP
get_claim(id=924488)