Unverified50% confidenceBenchmarkExact time
In a prompt injection defense evaluation, a certain decision model scored a perfect 40/40 on this test item.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/30/2026
First Seen
Valid until: 11/13/2026
Sources
Related Entities
Related Claims
UnverifiedOn the simplest items, the behavioral test overestimates faithfulness by as much as 20 percentage points.72% similarUnverified判断PMF的经验性指标包括Sean Ellis提出的40%测试、净推荐值NPS以及自然增长比例72% similarUnverifiedIn the comparative review's overall score, quality accounts for 40%, speed for 20%, and cost for 40%.71% similarUnverifiedEach question in the test is scored out of 100 points, consisting of 70 points for correctness plus 30 points for quality, with different questions carrying different weights.71% similarUnverified20–50 input/expected-output pairs should be retained as a test set and run on every prompt change, rather than relying on intuition.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1118378API
curl https://kongchang.com/api/v1/knowledge/claims/1118378MCP
get_claim(id=1118378)