Unverified50% confidenceBenchmarkExact time
The human baseline accuracy is 90.8%.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe per-step accuracy of current top-tier models is approximately between 90% and 95%.74% similarUnverifiedResearch shows that the agreement rate between LLM judges and human scores is approximately 80%, approaching but not yet surpassing the level of human inter-annotator agreement (approximately 81%).74% similarUnverifiedThe pass rate of top models in 2025 on the HumanEval benchmark has exceeded 90%.73% similarUnverified即便单字符识别准确率达到99%，对于一个包含10个字符的字段，其整体正确率也仅约90%，这被称为"准确率衰减效应"73% similarUnverifiedResearch shows that when humans assign 90% confidence, their actual accuracy rate is often only around 70%, indicating a systematic overconfidence71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/902501API
curl https://kongchang.com/api/v1/knowledge/claims/902501MCP
get_claim(id=902501)