Unverified50% confidenceBenchmarkExact time
At 81.0% decision coverage, the gated agent reached 60.0% agreement with recorded actions; the ungated ensemble agent had 55.0% agreement but coverage as high as 99.5%.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe majority-key baseline achieves 83.1% accuracy on movement keys, while each checkpoint's opponent-head accuracy ranges from 72.6% to 81.7%, with none exceeding the baseline.74% similarUnverifiedThe main agent's win rate against the scripted DuelBot was 98% to 99%, while an agent behavior-cloned from ranked replays won only 0% to 6% against these checkpoints.73% similarUnverifiedThe overall accuracy remains at just above 60%, indicating that automated annotation is still far from fully replacing human labor.72% similarUnverifiedMedIQ多智能体系统最终达到57%准确率,摘要智能体带来约5%提升,而拥有全部前置信息的Oracle上限为66%72% similarUnverifiedThis secondary scoring uses four weights: overall intelligence accounts for 60%, agent and terminal coding capability 20%, cost efficiency 10%, and output speed 10%.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1173908API
curl https://kongchang.com/api/v1/knowledge/claims/1173908MCP
get_claim(id=1173908)