Mathematical Reasoning on Omni-MATH (Avg@4 Accuracy)
28.16Avg@4 AccuracyReQueR
Evaluation Results
| Method | Links | |
|---|---|---|
| ReQueRModel=Qwen3-8B, Temperature=0.62026.04 | 28.16 | |
| CoTModel=Qwen3-8B, Temperature=0.62026.04 | 27.91 | |
| ReQueRModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 27.37 | |
| CoTModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 26.4 | |
| ReQueRModel=Qwen3-1.7B, Temperature=0.62026.04 | 22.11 | |
| CoTModel=Qwen3-1.7B, Temperature=0.62026.04 | 20.84 | |
| ReQueRModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 20.3 | |
| CoTModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 17.93 | |
| ReQueRModel=Qwen3-0.6B, Temperature=0.62026.04 | 15.18 | |
| ReQueRModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 14.02 | |
| ReQueRModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 13.48 | |
| CoTModel=Qwen3-0.6B, Temperature=0.62026.04 | 13.14 | |
| CoTModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 11.63 | |
| CoTModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 11.04 | |
| ReQueRModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 9.28 | |
| CoTModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 8.63 | |
| ReQueRModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 6.64 | |
| CoTModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 5.94 |