Unverified50% confidenceFactExact time
OSWorld 2.0中模型评估仅占总得分的11.53%，且没有任何任务的模型评估占比超过50%
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
OSWorld 2.0测评：最强AI Agent完成率仅20%，长流程是致命短板
bilibili熊二等兵7/1/2026
Related Claims
UnverifiedRoboDojo具身智能测评显示，最强模型得分仅12.8分（人类基准为100分），仿真成功率不足9%，真机成功率12.8%64% similarUnverified一个61分的模型和一个59分的模型在多数实际应用中的差异可能远小于分数暗示的程度58% similarUnverifiedIn the Agency tool-calling test, both models scored 95 points, and the only failure for both was task No. 13 (USD to JPY foreign currency conversion).58% similarUnverifiedDevin 2.0 resolved 13.86% of real-world programming problems in the SWE-bench benchmark, compared to only 1.96% for previous AI models.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/338173API
curl https://kongchang.com/api/v1/knowledge/claims/338173MCP
get_claim(id=338173)