Unverified50% confidenceBenchmarkExact time
Pathway报告称基于BDH的系统在约25万道Sudoku Extreme题目上达到97.4%的Top-1准确率,且未使用CoT、未进行解答回溯
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/14/2026
First Seen
Valid until: 10/12/2026
Sources
Related Claims
UnverifiedQwen3 27B在OpenAI HumanEval 164道Python题上取得85%通过率和99%应答率61% similarUnverified在15款大模型开发B站首页的测试中,ChatGPT 5.4以82分的总分获得全场第一61% similarUnverifiedMEME基准测试中表现最好的记忆系统MD-Flat整体准确率仅为0.4260% similarUnverifiedQwen3 27B在256K长上下文记忆检索测试(大海捞针)中取得100%通过率,15次运行全部准确60% similarUnverifiedbuffalo_l在MS1MV3数据集(约300万张图像)上训练,LFW准确率接近99.8%59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/507153API
curl https://kongchang.com/api/v1/knowledge/claims/507153MCP
get_claim(id=507153)