Unverified50% confidenceBenchmarkExact time
DK-VLM-8B achieved the highest average score across six spatial benchmarks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedDK-VLM scored 74.33 on VSI-Bench and 58.28 on ReVSI-32, both the highest total scores.64% similarUnverifiedAcross six configurations covering five groups of heterogeneous agent combinations, HMA improved the any-medal rate by an average of 6.4 percentage points over its constituent baseline agents.63% similarUnverifiedpplx-decider-v1-27b achieved an average score of 85.7% across 11 benchmarks, outperforming the comparison target Jev (official data).63% similarUnverifiedGLM-5.3在六项评测中的成绩为：终端编程基准3.0得28.3、深度软件工程基准得66.9、智能体中场考试得28.5、自动化基准得48.2、带工具的人类终极考试得62.5、GDP价值评估AA2版得17.6962% similarUnverified在HumanEval、MBPP、GSM8K等基准测试上，Gemma 7B的表现显著优于同参数量级的LLaMA 2 7B和Mistral 7B60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042455API
curl https://kongchang.com/api/v1/knowledge/claims/1042455MCP
get_claim(id=1042455)