Unverified50% confidenceBenchmarkExact time
在 BioPhys-Bridge 评测中,DeepSeek-V4-Flash 以证据ID的F1分数 0.360 取得最高分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/18/2026
First Seen
Valid until: 12/17/2026
Sources
Related Entities
Related Claims
Unverified在 BioPhys-Bridge 评测中,Qwen3.7-Max 的证据ID F1分数为 0.31678% 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68% similarUnverifiedDeepSeek V4 Pro在Humanity's Last Exam基准测试中得分37.765% similarUnverifiedMiniCPM5-2B在Artificial Analysis Intelligence Index v4.2基准测试中获得15分综合成绩,在4B参数以下开源模型中排名第一64% similarUnverified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63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931049API
curl https://kongchang.com/api/v1/knowledge/claims/931049MCP
get_claim(id=931049)