Unverified50% confidenceBenchmarkExact time
该模型的成功率比使用激光雷达与深度相机的多传感器系统还高 4.5 个百分点
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/16/2026
First Seen
Valid until: 10/14/2026
Sources
Related Claims
Unverified在实际性能测试中，GLM 4.6的表现远远优于Claude 4.5 Haiku61% similarUnverified在同一模型（Claude 4.6 Opus）下，OCR的精度（Precision）为33.9%，通用Agent为7.23%，OCR精度提升约4.7倍61% similarUnverified腾讯官方称混元3性能可比肩参数规模大2至5倍的旗舰模型59% similarUnverified响应时间只看厂商标称的1ms/0.5ms GtG意义不大，应看RTINGS等第三方实测的过冲(overshoot)数据，标称与实测常差2-3倍58% similarUnverifiedGPTQ于2022年通过逐层最优化二阶误差补偿实现了4位精度下的高质量模型压缩58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/536181API
curl https://kongchang.com/api/v1/knowledge/claims/536181MCP
get_claim(id=536181)