Event ·Multi-source

Tavus Griffin模型通过真人测试

Tavus开发的Griffin模型在面对面AI评估中得分3.83,接近真人3.92的分数。48%的测试者认为与Griffin的对话是真人互动。该模型在NVIDIA评分上领先第二名系统2.80分。Griffin采用一体化系统,能同时处理听、思考、说话和动画,减少延迟。

Current read

Tavus的Griffin模型48%测试者误认为真人,NVIDIA评分接近真人水平,一体化设计减少延迟。

9 sources83° AI heatLast updated 2026/10/1 17:44:38

Evidence

9 sources
Primary sourcerohanpaul_ai
View source
Related source 1shao__meng
View source
Related source 3TestingCatalog
View source
Related source 6@koltregaskes
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.