Language Reasoning on TruthfulQA
40.15AccuracyFP16
Evaluation Results
| Method | Links | |
|---|---|---|
| FP16Model=Qwen2.5-14B2026.03 | 40.15 | |
| NSDSModel=Qwen2.5-14B2026.03 | 31.58 | |
| KurtosisModel=Qwen2.5-14B2026.03 | 30.77 | |
| ZDModel=Qwen2.5-14B2026.03 | 30.45 | |
| MSEModel=Qwen2.5-14B2026.03 | 29.63 | |
| EWQModel=Qwen2.5-14B2026.03 | 28.44 | |
| FP16Model=Llama-2-13B2026.03 | 25.95 | |
| NSDSModel=Llama-2-13B2026.03 | 23.86 | |
| KurtBoostModel=Llama-2-13B2026.03 | 23.04 | |
| EWQModel=Llama-2-13B2026.03 | 22.85 | |
| ZDModel=Llama-2-13B2026.03 | 22.23 | |
| MSEModel=Llama-2-13B2026.03 | 21.96 |