Unverified50% confidenceBenchmarkExact time
In the nine settings, NatScale achieves the highest value on the Top-token agreement rate metric in all cases.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedAcross all nine settings, NatScale achieves the lowest native-to-quantized KL divergence.65% similarUnverifiedThe first metric is Effective Rank, which measures in a continuous manner how many directions the Jacobian matrix truly acts upon.65% similarUnverifiedTop-1% accuracy is a metric for evaluating the output consistency between a quantized model and the original full-precision model, focusing on whether the top 1% of tokens with the highest model confidence are consistent with the full-precision version.64% similarUnverifiedThe Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).63% similarUnverifiedThe Top3 configuration, which uses the fewest metrics, achieved the highest average performance, indicating that fewer metrics actually yield higher performance under this experimental setting.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032972API
curl https://kongchang.com/api/v1/knowledge/claims/1032972MCP
get_claim(id=1032972)