Mathematical Reasoning on GSM-Symbolic Origin 100
96AccuracyCoT-RL
Evaluation results
| Method | Links | |
|---|---|---|
| CoT-RLModel=Qwen2.5-Math-7B-Instruct2025.06 | 96 | |
| CoT-8SModel=Qwen2.5-Math-7B-Instruct2025.06 | 95 | |
| CoT-8SModel=Qwen2.5-7B-Instruct2025.06 | 92 | |
| AbstRaLModel=Qwen2.5-Math-7B-Instruct2025.06 | 91 | |
| AbstRaLModel=Qwen2.5-7B-Instruct2025.06 | 89 | |
| CoT-8SModel=Llama-3.1-8B-Instruct2025.06 | 87 | |
| AbstRaLModel=Llama-3.1-8B-Instruct2025.06 | 87 | |
| CoT-RLModel=Qwen2.5-7B-Instruct2025.06 | 85 | |
| CoT-8SModel=Llama-3.2-3B-Instruct2025.06 | 84 | |
| CoT-RLModel=Llama-3.1-8B-Instruct2025.06 | 83 | |
| CoT-8SModel=Qwen2.5-3B-Instruct2025.06 | 82 | |
| AbstRaLModel=Mathstral-7B-v0.12025.06 | 81 | |
| CoT-RLModel=Llama-3.2-3B-Instruct2025.06 | 80 | |
| AbstRaLModel=Llama-3.2-3B-Instruct2025.06 | 80 | |
| CoT-8SModel=Mathstral-7B-v0.12025.06 | 80 | |
| CoT-RLModel=Qwen2.5-3B-Instruct2025.06 | 79 | |
| AbstRaLModel=Qwen2.5-3B-Instruct2025.06 | 79 | |
| CoT-RLModel=Mathstral-7B-v0.12025.06 | 78 | |
| CoAModel=Qwen2.5-7B-Instruct2025.06 | 76 | |
| CoAModel=Mathstral-7B-v0.12025.06 | 75 | |
| CoAModel=Llama-3.1-8B-Instruct2025.06 | 72 | |
| CoAModel=Qwen2.5-Math-7B-Instruct2025.06 | 71 | |
| CoAModel=Llama-3.2-3B-Instruct2025.06 | 68 | |
| CoT-8SModel=Qwen2.5-1.5B-Instruct2025.06 | 66 | |
| AbstRaLModel=Qwen2.5-1.5B-Instruct2025.06 | 65 | |
| CoAModel=Qwen2.5-3B-Instruct2025.06 | 65 | |
| AbstRaLModel=Llama-3.2-1B-Instruct2025.06 | 60 | |
| CoT-RLModel=Llama-3.2-1B-Instruct2025.06 | 57 | |
| CoT-RLModel=Qwen2.5-1.5B-Instruct2025.06 | 56 | |
| CoAModel=Qwen2.5-1.5B-Instruct2025.06 | 51 | |
| CoT-8SModel=Llama-3.2-1B-Instruct2025.06 | 48 | |
| CoAModel=Llama-3.2-1B-Instruct2025.06 | 46 | |
| AbstRaLModel=Qwen2.5-0.5B-Instruct2025.06 | 44 | |
| CoT-8SModel=Qwen2.5-0.5B-Instruct2025.06 | 38 | |
| CoT-RLModel=Qwen2.5-0.5B-Instruct2025.06 | 35 | |
| CoAModel=Qwen2.5-0.5B-Instruct2025.06 | 29 |