Expired50% confidenceBenchmarkExact time
On simple visual perception tasks, ordinary humans can achieve over 90% accuracy, while most SOTA models achieve only 50% or even lower.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/16/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/14/2026(expired)
Sources
Related Claims
UnverifiedOn cognitive tasks, humans can achieve approximately 80%, while SOTA multimodal models achieve only 30% to 50%, sometimes approaching random guessing77% similarUnverifiedExperimental data shows that when key information is located at the beginning and end of the input sequence, the model's retrieval accuracy can be as high as over 90%, but when located in the middle, it may drop sharply to below 60%.73% similarUnverifiedIn scenarios where AI-generated works account for a low proportion (e.g., only 5%), even with a detection accuracy of 90%, more than two-thirds of the flagged works are actually human-created—this is the base rate fallacy in Bayesian reasoning.72% similarUnverifiedAI intent recognition accuracy generally falls between 85% and 95%.70% similarUnverifiedThe metrics of over 90% accuracy and completion within one day were achieved in specific scenarios (such as visual reasoning at traffic intersections), and actual results vary depending on data quality and task complexity.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/533784API
curl https://kongchang.com/api/v1/knowledge/claims/533784MCP
get_claim(id=533784)