Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful content detection on Trolling-oriented generations DeepSeek-Llama 70B
Loading...
16.24
Accuracy
Perspective API
5.8192
8.5246
11.23
13.9354
Apr 18, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Perspective API
2026.04
16.24
OpenAI Moderation
2026.04
15.03
LlamaGuard-2
2026.04
10.06
LlamaGuard-1
2026.04
6.22
Feedback
Search any
task
Search any
task