Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful content detection on MT-CONAN
Loading...
97.24
Accuracy
LlamaGuard-1
85.8936
88.8393
91.785
94.7307
Apr 18, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
LlamaGuard-1
2026.04
97.24
LlamaGuard-1
2026.04
97.24
Perspective API
2026.04
95.42
Perspective API
2026.04
95.42
OpenAI Moderation
2026.04
93.24
OpenAI Moderation
2026.04
93.24
LlamaGuard-2
2026.04
86.33
LlamaGuard-2
2026.04
86.33
Feedback
Search any
task
Search any
task