Unverified50% confidenceFactExact time
OpenAPPA's README claims that none of the 1,320 evaluated attacks succeeded in being scored, while completing 88% to 90% of tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe task success rate of mainstream AI generation APIs is typically between 92% and 98%, meaning 2–8 out of every 100 tasks may fail.70% similarUnverifiedActionable Agent evaluation thresholds include a task decomposition rate and tool selection accuracy of 90% or above, a closed-loop completion rate of no less than 85%, and an error recovery rate of no less than 80%.66% similarUnverifiedIn tasks with propositional constraints, the proportion of models integrating candidates already verified as invalid is as high as 93%–100%.66% similarUnverified传统的成功率指标难以全面反映策略的鲁棒性，一个策略可能在90%的常规任务中表现出色却在剩余10%的关键场景中出现灾难性失败65% similarUnverifiedWithout guardrails, the agent completed 92% to 97% of tasks; with OpenAPPA added, DeepSeek dropped to 74%, Luna to 75%, and Gemini to 81%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006128API
curl https://kongchang.com/api/v1/knowledge/claims/1006128MCP
get_claim(id=1006128)