Mathematical Reasoning on GSM-Symbolic (Avg@4 accuracy)
88.12Avg@4 AccuracyReQueR
Evaluation Results
| Method | Links | |
|---|---|---|
| ReQueRModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 88.12 | |
| ReQueRModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 87.98 | |
| ReQueRModel=Qwen3-8B, Temperature=0.62026.04 | 87.08 | |
| CoTModel=Qwen3-8B, Temperature=0.62026.04 | 86.96 | |
| CoTModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 85.76 | |
| CoTModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 82.26 | |
| ReQueRModel=Qwen3-1.7B, Temperature=0.62026.04 | 78.64 | |
| ReQueRModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 75.82 | |
| CoTModel=Qwen3-1.7B, Temperature=0.62026.04 | 74.62 | |
| CoTModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 74.44 | |
| ReQueRModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 69.38 | |
| ReQueRModel=Qwen3-0.6B, Temperature=0.62026.04 | 66.14 | |
| CoTModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 60.64 | |
| ReQueRModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 59.66 | |
| CoTModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 52.12 | |
| CoTModel=Qwen3-0.6B, Temperature=0.62026.04 | 50.8 | |
| ReQueRModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 48.34 | |
| CoTModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 39.48 |