Unverified50% confidenceBenchmarkExact time
作为对照的简单三规则基线(3-rule baseline)准确率仅为64.4%,Jev领先约8个百分点
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/21/2026
First Seen
Valid until: 12/20/2026
Sources
Related Entities
Related Claims
UnverifiedClaude Opus 4.7中间检查点通过率达57%,最终准确率却只有39.8%76% similarUnverified引导模式下平均端到端准确率从28.6%提升到33.7%,歧义检测F1值从45.3%提升到64.9%69% similarUnverifiedGLM4在代码推理和通用知识测试中得分74.4%,仅次于Claude 3 Opus69% similarUnverified通义千问3.6 27B在语义三次全对率和格式正确率上均领先Muse Glimmer68% similarUnverifiedQwen 3.6 Max在中性模式下端到端准确率仅12.3%68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/937908API
curl https://kongchang.com/api/v1/knowledge/claims/937908MCP
get_claim(id=937908)