Unverified50% confidenceBenchmarkExact time
The model's generalization ability on fonts never seen during training is approximately 59% top-1, only 6 points below the 65% achieved on seen fonts.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn evaluation suite with 1,800 test cases has long maintained a stable aggregate pass rate of 97%, but the 64-case multilingual slice within it has a pass rate of only 61%65% similarUnverifiedThe traditional expert codebook revision approach achieved an LLM annotation accuracy of only 57.8%.63% similarUnverifiedOn repeated questions, index reinforcement raised the top-1 hit rate from 0.571 to 0.743 without any model training throughout the process.63% similarUnverifiedOn τ2-bench, as many as 57% of the teacher model's trials are failures.62% similarUnverified一个61分的模型和一个59分的模型在多数实际应用中的差异可能远小于分数暗示的程度62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/997215API
curl https://kongchang.com/api/v1/knowledge/claims/997215MCP
get_claim(id=997215)