Unverified50% confidenceFactExact time
Even after fine-tuning to reach 65.7% accuracy, there is still a considerable gap from the human level of 87.2%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedResearch 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%).72% similarUnverified63%的提升幅度是相对于基线的相对提升，而非绝对准确率的提升71% similarUnverifiedUnder the condition of n=100 with an even split of positive and negative samples, the 95% confidence interval for 55% accuracy is roughly 45%–65%, which covers the 50% baseline, so the 5 percentage point gap may be random fluctuation.70% similarUnverifiedAn accuracy of 85% represents a significant advance in research terms, but still falls short of the reliability threshold required for clinical use.70% similarUnverifiedWhen a 61% pass rate is observed on 64 samples, the 95% Wilson confidence interval is approximately 48% to 73%69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013361API
curl https://kongchang.com/api/v1/knowledge/claims/1013361MCP
get_claim(id=1013361)