Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Hijacking on IHEval Prompt Hijacking Conflict 1.0
Loading...
45
Accuracy
Qwen3-4B-it-NSHA-SFT
7.04
16.895
26.75
36.605
Apr 10, 2026
Accuracy
Updated 6d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-4B-it-NSHA-SFT
Backbone=Qwen3-4B, Met...
2026.04
45
Llama3.1-8B-NSHA-DPO
Backbone=Llama3.1-8B,...
2026.04
30.6
Llama3.1-8B-NSHA-SFT
Backbone=Llama3.1-8B,...
2026.04
27.5
Llama3.1-8B-NSHA-HCAL
Backbone=Llama3.1-8B,...
2026.04
20.1
Llama3.1-8B-NS
Backbone=Llama3.1-8B,...
2026.04
19.7
Llama3.1-8B
Backbone=Llama3.1-8B,...
2026.04
19.3
Llama3.1-8B-CoT
Backbone=Llama3.1-8B,...
2026.04
17
Qwen3-4B-it-NS
Backbone=Qwen3-4B, Met...
2026.04
13.8
Qwen3-4B-it
Backbone=Qwen3-4B, Met...
2026.04
13.1
Qwen3-4B-it-NSHA-HCAL
Backbone=Qwen3-4B, Met...
2026.04
12.5
Qwen3-4B-it-NSHA-DPO
Backbone=Qwen3-4B, Met...
2026.04
9.8
Qwen3-4B-it-CoT
Backbone=Qwen3-4B, Met...
2026.04
8.5
Feedback
Search any
task
Search any
task