Unverified50% confidenceFactExact time
良好判断团队的预测准确率持续以约30%的优势领先其他专业情报分析机构
1
Sources
50%
Confidence
Long-term
Relevance
7/7/2026
First Seen
Sources
AI超级预测者：机器能否超越人类专家的预测能力？
hackernewshackernews7/6/2026
Related Claims
Unverified根据Artificial Analysis的独立评测，Glimmer 30B的智能指数得分为35分61% 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%60% similarUnverifiedArtificial Analysis给Muse Glimmer 30B打出35分的智能指数，相比Llama 4 Maverick是巨大飞跃60% similarUnverified测试者评估Codex大概能完成看板上30%的任务58% similarUnverified评测者认为通义千问3.6 27B是30B级别中对高考数学题表现最好的模型56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/180113API
curl https://kongchang.com/api/v1/knowledge/claims/180113MCP
get_claim(id=180113)