List your company

Web browsing on WebShop

92.6TSRFragFuse
14.80835.00455.275.396Jun 14, 2026

Evaluation results

MethodLinks
FragFuseAccess Control=GuardAgent, Core LLM=GPT-4o2026.0692.681
FragFuseAccess Control=LLM-AC, Core LLM=GPT-4o2026.0692.593
direct queryingAccess Control=None, Core LLM=GPT-4o2026.0688—
direct queryingAccess Control=None, Core LLM=Gemini 2.5 Flash2026.0688—
direct queryingAccess Control=None, Core LLM=Average2026.0683.7—
FragFuseAccess Control=GuardAgent, Core LLM=Average2026.0682.279.3
FragFuseAccess Control=GuardAgent, Core LLM=GPT-5.12026.0678.684
FragFuseAccess Control=LLM-AC, Core LLM=Average2026.0677.693.7
baselineAccess Control=LLM-AC, Core LLM=GPT-4o2026.0677.540
baselineAccess Control=GuardAgent, Core LLM=GPT-4o2026.0676.242
FragFuseAccess Control=GuardAgent, Core LLM=Gemini 2.5 Flash2026.0675.373
direct queryingAccess Control=None, Core LLM=GPT-5.12026.0675—
FragFuseAccess Control=LLM-AC, Core LLM=GPT-5.12026.0670.498
FragFuseAccess Control=LLM-AC, Core LLM=Gemini 2.5 Flash2026.067090
baselineAccess Control=LLM-AC, Core LLM=Gemini 2.5 Flash2026.0666.76
baselineAccess Control=LLM-AC, Core LLM=Average2026.065430.3
baselineAccess Control=GuardAgent, Core LLM=Gemini 2.5 Flash2026.0653.813
baselineAccess Control=GuardAgent, Core LLM=Average2026.0651.835.3
baselineAccess Control=GuardAgent, Core LLM=GPT-5.12026.0625.551
baselineAccess Control=LLM-AC, Core LLM=GPT-5.12026.0617.845