Unverified50% confidenceBenchmarkExact time
MDT在第三届ABAW挑战赛的BAH数据集有标签测试集上取得0.7408的宏平均F1，在私有排行榜上取得0.7368的Macro F1
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在 BioPhys-Bridge 评测中，Qwen3.7-Max 的证据ID F1分数为 0.31669% similarUnverifiedCriticGen在基于标准的理由和可执行建议上的F1分数分别从0.6369/0.5994提升到0.7554/0.790066% similarUnverifiedQwen 3.6 Max中性模式下歧义检测F1仅16%，平均每任务只问0.07个问题，但一旦提问澄清准确率高达94.7%64% similarUnverifiedAccording to the MedViT paper, the model achieved a Macro F1 score of 0.7791 on ChestX-ray1463% similarUnverified当每个目标的雷达检测点从1个增加到5个时，Macro F1从0.381跃升至0.76461% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931304API
curl https://kongchang.com/api/v1/knowledge/claims/931304MCP
get_claim(id=931304)