Mathematical Reasoning on OlympiadBench (Avg@4 accuracy)
51.45Avg@4 AccuracyReQueR
Evaluation Results
| Method | Links | |
|---|---|---|
| ReQueRModel=Qwen3-8B, Temperature=0.62026.04 | 51.45 | |
| CoTModel=Qwen3-8B, Temperature=0.62026.04 | 50 | |
| ReQueRModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 46.44 | |
| CoTModel=Qwen2.5-72B-Instruct, Temperature=0.62026.04 | 43.62 | |
| ReQueRModel=Qwen3-1.7B, Temperature=0.62026.04 | 39.02 | |
| CoTModel=Qwen3-1.7B, Temperature=0.62026.04 | 37.83 | |
| ReQueRModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 36.05 | |
| CoTModel=Llama-3.1-70B-Instruct, Temperature=0.62026.04 | 31.31 | |
| ReQueRModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 21.81 | |
| ReQueRModel=Qwen3-0.6B, Temperature=0.62026.04 | 21.66 | |
| ReQueRModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 19.88 | |
| CoTModel=Qwen3-0.6B, Temperature=0.62026.04 | 19.14 | |
| CoTModel=Llama-3.1-8B-Instruct, Temperature=0.62026.04 | 16.02 | |
| CoTModel=Llama-3.2-3B-Instruct, Temperature=0.62026.04 | 12.76 | |
| ReQueRModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 10.68 | |
| CoTModel=Mixtral-8x7B-Instruct, Temperature=0.62026.04 | 7.12 | |
| ReQueRModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 3.56 | |
| CoTModel=DS-MoE-16B-Chat, Temperature=0.62026.04 | 2.52 |