Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Extraction on IHEval Prompt Extraction - Conflict 1.0
Loading...
59.6
Accuracy
Qwen3-4B-it-NSHA-SFT
9.056
22.178
35.3
48.422
Apr 10, 2026
Accuracy
Updated 6d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-4B-it-NSHA-SFT
Backbone=Qwen3-4B, Met...
2026.04
59.6
Llama3.1-8B-NSHA-SFT
Backbone=Llama3.1-8B,...
2026.04
36.3
Qwen3-4B-it
Backbone=Qwen3-4B, Met...
2026.04
25.6
Qwen3-4B-it-NS
Backbone=Qwen3-4B, Met...
2026.04
25.5
Qwen3-4B-it-NSHA-HCAL
Backbone=Qwen3-4B, Met...
2026.04
24
Qwen3-4B-it-NSHA-DPO
Backbone=Qwen3-4B, Met...
2026.04
20.3
Llama3.1-8B-NSHA-DPO
Backbone=Llama3.1-8B,...
2026.04
17.5
Qwen3-4B-it-CoT
Backbone=Qwen3-4B, Met...
2026.04
15.9
Llama3.1-8B-NSHA-HCAL
Backbone=Llama3.1-8B,...
2026.04
12.1
Llama3.1-8B
Backbone=Llama3.1-8B,...
2026.04
11.3
Llama3.1-8B-NS
Backbone=Llama3.1-8B,...
2026.04
11.3
Llama3.1-8B-CoT
Backbone=Llama3.1-8B,...
2026.04
11
Feedback
Search any
task
Search any
task