Mathematical Reasoning on GSM-Symbolic Vary Name
92.48AccuracyAbstRaL
Evaluation Results
| Method | Links | |
|---|---|---|
| AbstRaLModel=Qwen2.5-7B-Instruct2025.06 | 92.48 | |
| CoT-8SModel=Qwen2.5-7B-Instruct2025.06 | 92.3 | |
| CoT-RLModel=Qwen2.5-Math-7B-Instruct2025.06 | 91.54 | |
| CoT-8SModel=Qwen2.5-Math-7B-Instruct2025.06 | 91.08 | |
| AbstRaLModel=Qwen2.5-Math-7B-Instruct2025.06 | 90.14 | |
| CoT-8SModel=Llama-3.1-8B-Instruct2025.06 | 87.46 | |
| CoT-RLModel=Llama-3.1-8B-Instruct2025.06 | 87.1 | |
| AbstRaLModel=Llama-3.1-8B-Instruct2025.06 | 86.72 | |
| AbstRaLModel=Mathstral-7B-v0.12025.06 | 82.14 | |
| CoT-RLModel=Qwen2.5-7B-Instruct2025.06 | 81.7 | |
| CoT-8SModel=Mathstral-7B-v0.12025.06 | 80.84 | |
| CoT-RLModel=Mathstral-7B-v0.12025.06 | 79.86 | |
| AbstRaLModel=Llama-3.2-3B-Instruct2025.06 | 79.82 | |
| AbstRaLModel=Qwen2.5-3B-Instruct2025.06 | 78.52 | |
| CoT-8SModel=Qwen2.5-3B-Instruct2025.06 | 78.2 | |
| CoAModel=Mathstral-7B-v0.12025.06 | 77.4 | |
| CoT-RLModel=Qwen2.5-3B-Instruct2025.06 | 77.06 | |
| CoT-8SModel=Llama-3.2-3B-Instruct2025.06 | 76.38 | |
| CoT-RLModel=Llama-3.2-3B-Instruct2025.06 | 75.16 | |
| CoAModel=Qwen2.5-7B-Instruct2025.06 | 74.08 | |
| CoAModel=Llama-3.1-8B-Instruct2025.06 | 70.86 | |
| CoAModel=Qwen2.5-Math-7B-Instruct2025.06 | 69.76 | |
| CoAModel=Llama-3.2-3B-Instruct2025.06 | 68.02 | |
| CoT-8SModel=Qwen2.5-1.5B-Instruct2025.06 | 64.16 | |
| AbstRaLModel=Qwen2.5-1.5B-Instruct2025.06 | 64.14 | |
| CoAModel=Qwen2.5-3B-Instruct2025.06 | 61.34 | |
| AbstRaLModel=Llama-3.2-1B-Instruct2025.06 | 58.38 | |
| CoT-RLModel=Qwen2.5-1.5B-Instruct2025.06 | 58.3 | |
| CoT-RLModel=Llama-3.2-1B-Instruct2025.06 | 53.42 | |
| CoAModel=Qwen2.5-1.5B-Instruct2025.06 | 49.42 | |
| AbstRaLModel=Qwen2.5-0.5B-Instruct2025.06 | 44.16 | |
| CoAModel=Llama-3.2-1B-Instruct2025.06 | 43.72 | |
| CoT-8SModel=Llama-3.2-1B-Instruct2025.06 | 42.5 | |
| CoT-RLModel=Qwen2.5-0.5B-Instruct2025.06 | 39.48 | |
| CoT-8SModel=Qwen2.5-0.5B-Instruct2025.06 | 37.24 | |
| CoAModel=Qwen2.5-0.5B-Instruct2025.06 | 30.6 |