Unverified50% confidenceBenchmarkExact time
Wolf Defender v2's attack detection capability is largely maintained at its original level, with a Qualifire F1 of 95.14% and a Jayavibhav F1 of 97.84%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/31/2026
First Seen
Valid until: 11/29/2026
Sources
Related Entities
Related Claims
UnverifiedThe Wolf Defender main model's real-world benign specificity improved from 66.85% in v1 to 96.63% in v2.76% similarUnverifiedWolf Defender v2 employs mixed training combining short samples (256 tokens) with a full long window (2048 tokens).62% similarUnverifiedIn guided mode, the average end-to-end accuracy increased from 28.6% to 33.7%, and the ambiguity detection F1 score increased from 45.3% to 64.9%52% similarUnverifiedAccording to the MedViT paper, the model achieved a Macro F1 score of 0.7791 on ChestX-ray1451% similarUnverifiedLFM2.5 improved by 19 and 23 points respectively over the previous generation in the BFCL-v3 and BFCL-v4 tool-calling evaluations.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/827599API
curl https://kongchang.com/api/v1/knowledge/claims/827599MCP
get_claim(id=827599)