Get Webpage on IHEval v1 (Reference)
86AccuracyLlama3.1-8B-NSHA-HCAL
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama3.1-8B-NSHA-HCALBackbone=Llama3.1-8B, Alignment=NSHA-HCAL2026.04 | 86 | |
| Llama3.1-8B-NSBackbone=Llama3.1-8B, Inference Mode=Neuro-Symbolic2026.04 | 85.8 | |
| Llama3.1-8BBackbone=Llama3.1-8B2026.04 | 85.2 | |
| Qwen3-4B-it-NSHA-SFTBackbone=Qwen3-4B-it, Alignment=NSHA-SFT2026.04 | 81.1 | |
| Qwen3-4B-it-NSBackbone=Qwen3-4B-it, Inference Mode=Neuro-Symbolic2026.04 | 79.9 | |
| Qwen3-4B-itBackbone=Qwen3-4B-it2026.04 | 79.7 | |
| Qwen3-4B-it-NSHA-HCALBackbone=Qwen3-4B-it, Alignment=NSHA-HCAL2026.04 | 79.5 | |
| Qwen3-4B-it-NSHA-DPOBackbone=Qwen3-4B-it, Alignment=NSHA-DPO2026.04 | 79 | |
| Llama3.1-8B-NSHA-DPOBackbone=Llama3.1-8B, Alignment=NSHA-DPO2026.04 | 79 | |
| Qwen3-4B-it-CoTBackbone=Qwen3-4B-it, Inference Mode=Chain-of-Thought2026.04 | 77.6 | |
| Llama3.1-8B-CoTBackbone=Llama3.1-8B, Inference Mode=Chain-of-Thought2026.04 | 74.2 | |
| Llama3.1-8B-NSHA-SFTBackbone=Llama3.1-8B, Alignment=NSHA-SFT2026.04 | 24.9 |