Expired50% confidenceBenchmarkExact time
On cognitive tasks, humans can achieve approximately 80%, while SOTA multimodal models achieve only 30% to 50%, sometimes approaching random guessing
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/17/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/15/2026(expired)
Sources
Related Claims
UnverifiedOn simple visual perception tasks, ordinary humans can achieve over 90% accuracy, while most SOTA models achieve only 50% or even lower.77% 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.75% similarUnverified研究表明在要求AI直接生成参考文献的任务中，幻觉率可高达40%-70%72% similarUnverified根据文中量化估算，编程智能体任务中模型推理仅占总时间的 20%-30%，剩余 70%-80% 花在等待外部系统 I/O 响应72% similarVerifiedResearch shows that even the most advanced models have hallucination rates in factual question-answering tasks that still fluctuate between 5% and 20%.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/544829API
curl https://kongchang.com/api/v1/knowledge/claims/544829MCP
get_claim(id=544829)