Unverified50% confidenceFactExact time
In the illustrative sample constructed in the article, a certain tool's first-call success rate was 76% on the claude-desktop client and 21% on cursor, with an average of 62% across all clients.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
UnverifiedFor comparison, the Program-of-Thought baseline achieves 72.0% overall accuracy and the tool-calling agent achieves 58.7%.71% similarUnverifiedAnthropic 官方承认 Computer Use 在复杂任务上的成功率仅约 60-70%70% similarUnverifiedUsing only synthetic weak instructions fed directly into the navigator, the success rate was 15.27%, falling between the exhaustive command rate of 31.03% and the real user instruction rate of 11.33%.69% similarUnverified在歧义点的四类行为中，'先搜再问'成功率最高，平均通过率达93.4%，远高于'直接猜'的56.5%，'搜多次再猜'为51.5%66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034244API
curl https://kongchang.com/api/v1/knowledge/claims/1034244MCP
get_claim(id=1034244)