List your company

Get Webpage on IHEval v1 (Conflict)

39.8AccuracyQwen3-4B-it-CoT
0.38410.61720.8531.083Apr 10, 2026

Evaluation results

MethodLinks
Qwen3-4B-it-CoTBackbone=Qwen3-4B-it, Inference Mode=Chain-of-Thought2026.0439.8
Qwen3-4B-it-NSHA-DPOBackbone=Qwen3-4B-it, Alignment=NSHA-DPO2026.0436.9
Qwen3-4B-it-NSHA-HCALBackbone=Qwen3-4B-it, Alignment=NSHA-HCAL2026.0436.3
Qwen3-4B-it-NSBackbone=Qwen3-4B-it, Inference Mode=Neuro-Symbolic2026.0436.2
Qwen3-4B-it-NSHA-SFTBackbone=Qwen3-4B-it, Alignment=NSHA-SFT2026.0431.6
Llama3.1-8B-NSBackbone=Llama3.1-8B, Inference Mode=Neuro-Symbolic2026.0412.7
Llama3.1-8B-NSHA-HCALBackbone=Llama3.1-8B, Alignment=NSHA-HCAL2026.0411.5
Llama3.1-8B-CoTBackbone=Llama3.1-8B, Inference Mode=Chain-of-Thought2026.049.2
Llama3.1-8BBackbone=Llama3.1-8B2026.047.8
Llama3.1-8B-NSHA-DPOBackbone=Llama3.1-8B, Alignment=NSHA-DPO2026.045
Llama3.1-8B-NSHA-SFTBackbone=Llama3.1-8B, Alignment=NSHA-SFT2026.044.1
Qwen3-4B-itBackbone=Qwen3-4B-it2026.041.9