Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Slack User on IHEval v1 (Conflict)
Loading...
80
Accuracy
Qwen3-4B-it-CoT
-3.2
18.4
40
61.6
Apr 10, 2026
Accuracy
Updated 6d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-4B-it-CoT
Backbone=Qwen3-4B-it,...
2026.04
80
Qwen3-4B-it-NS
Backbone=Qwen3-4B-it,...
2026.04
77
Qwen3-4B-it-NSHA-DPO
Backbone=Qwen3-4B-it,...
2026.04
76
Qwen3-4B-it-NSHA-HCAL
Backbone=Qwen3-4B-it,...
2026.04
74.5
Qwen3-4B-it-NSHA-SFT
Backbone=Qwen3-4B-it,...
2026.04
58
Llama3.1-8B-NSHA-HCAL
Backbone=Llama3.1-8B,...
2026.04
32.5
Llama3.1-8B-NS
Backbone=Llama3.1-8B,...
2026.04
32
Llama3.1-8B-CoT
Backbone=Llama3.1-8B,...
2026.04
30
Llama3.1-8B-NSHA-SFT
Backbone=Llama3.1-8B,...
2026.04
6.5
Qwen3-4B-it
Backbone=Qwen3-4B-it
2026.04
1
Llama3.1-8B
Backbone=Llama3.1-8B
2026.04
0
Llama3.1-8B-NSHA-DPO
Backbone=Llama3.1-8B,...
2026.04
0
Feedback
Search any
task
Search any
task