Mathematical Reasoning on AMC 23 (Avg@4 accuracy)
68.13Avg@4 AccuracyReQueR
Evaluation Results
| Method | Links | |
|---|---|---|
| ReQueRModel=Qwen3-8B, Temperature=0.62026.04 | 68.13 | |
| CoTModel=Qwen3-8B, Temperature=0.62026.04 | 65.31 | |
| ReQueRModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 62.5 | |
| CoTModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 61.88 | |
| ReQueRModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 53.75 | |
| CoTModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 50.31 | |
| ReQueRModel=Qwen3-1.7B, Temperature=0.62026.04 | 43.13 | |
| CoTModel=Qwen3-1.7B, Temperature=0.62026.04 | 41.25 | |
| ReQueRModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 30.94 | |
| CoTModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 25.94 | |
| ReQueRModel=Qwen3-0.6B, Temperature=0.62026.04 | 23.75 | |
| ReQueRModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 22.19 | |
| CoTModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 19.69 | |
| CoTModel=Qwen3-0.6B, Temperature=0.62026.04 | 18.44 | |
| ReQueRModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 18.12 | |
| CoTModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 9.69 | |
| ReQueRModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 7.19 | |
| CoTModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 6.25 |