Language Reasoning on Language Reasoning Average
73.25AccuracyFP16
Evaluation Results
| Method | Links | |
|---|---|---|
| FP16Backbone=Qwen2.5-14B2026.03 | 73.25 | |
| FP16Backbone=Llama-2-13B2026.03 | 67.23 | |
| NSDSBackbone=Qwen2.5-14B2026.03 | 66.15 | |
| ZDBackbone=Qwen2.5-14B2026.03 | 65.42 | |
| KurtBoostBackbone=Qwen2.5-14B2026.03 | 65.13 | |
| MSEBackbone=Qwen2.5-14B2026.03 | 64.29 | |
| EWQBackbone=Qwen2.5-14B2026.03 | 63.36 | |
| NSDSBackbone=Llama-2-13B2026.03 | 63.01 | |
| KurtBoostBackbone=Llama-2-13B2026.03 | 62.08 | |
| EWQBackbone=Llama-2-13B2026.03 | 61.68 | |
| ZDBackbone=Llama-2-13B2026.03 | 60.99 | |
| MSEBackbone=Llama-2-13B2026.03 | 59.91 |