Mathematical Reasoning on GSM-Symbolic Vary Num.
90.66AccuracyAbstRaL
Evaluation Results
| Method | Links | |
|---|---|---|
| AbstRaLModel=Qwen2.5-Math-7B-Instruct2025.06 | 90.66 | |
| AbstRaLModel=Qwen2.5-7B-Instruct2025.06 | 90.22 | |
| CoT-8SModel=Qwen2.5-Math-7B-Instruct2025.06 | 89.56 | |
| CoT-RLModel=Qwen2.5-Math-7B-Instruct2025.06 | 89.42 | |
| CoT-8SModel=Qwen2.5-7B-Instruct2025.06 | 87.26 | |
| AbstRaLModel=Llama-3.1-8B-Instruct2025.06 | 86.86 | |
| CoT-8SModel=Llama-3.1-8B-Instruct2025.06 | 84.4 | |
| AbstRaLModel=Mathstral-7B-v0.12025.06 | 81 | |
| CoT-RLModel=Mathstral-7B-v0.12025.06 | 80.82 | |
| AbstRaLModel=Llama-3.2-3B-Instruct2025.06 | 79.6 | |
| CoT-8SModel=Mathstral-7B-v0.12025.06 | 78.76 | |
| AbstRaLModel=Qwen2.5-3B-Instruct2025.06 | 78.42 | |
| CoT-RLModel=Llama-3.1-8B-Instruct2025.06 | 77.84 | |
| CoT-RLModel=Qwen2.5-7B-Instruct2025.06 | 77.7 | |
| CoAModel=Mathstral-7B-v0.12025.06 | 75.06 | |
| CoAModel=Qwen2.5-7B-Instruct2025.06 | 73.1 | |
| CoAModel=Llama-3.1-8B-Instruct2025.06 | 72.4 | |
| CoT-8SModel=Qwen2.5-3B-Instruct2025.06 | 72.22 | |
| CoT-8SModel=Llama-3.2-3B-Instruct2025.06 | 72.18 | |
| CoT-RLModel=Qwen2.5-3B-Instruct2025.06 | 71.5 | |
| CoAModel=Qwen2.5-Math-7B-Instruct2025.06 | 71.22 | |
| CoT-RLModel=Llama-3.2-3B-Instruct2025.06 | 70.56 | |
| CoAModel=Llama-3.2-3B-Instruct2025.06 | 64.5 | |
| AbstRaLModel=Qwen2.5-1.5B-Instruct2025.06 | 64.44 | |
| CoAModel=Qwen2.5-3B-Instruct2025.06 | 64.24 | |
| AbstRaLModel=Llama-3.2-1B-Instruct2025.06 | 59.12 | |
| CoT-8SModel=Qwen2.5-1.5B-Instruct2025.06 | 57.28 | |
| CoT-RLModel=Qwen2.5-1.5B-Instruct2025.06 | 52.96 | |
| CoT-RLModel=Llama-3.2-1B-Instruct2025.06 | 47.88 | |
| CoAModel=Qwen2.5-1.5B-Instruct2025.06 | 46.8 | |
| CoAModel=Llama-3.2-1B-Instruct2025.06 | 45.34 | |
| AbstRaLModel=Qwen2.5-0.5B-Instruct2025.06 | 43.96 | |
| CoT-8SModel=Llama-3.2-1B-Instruct2025.06 | 38.64 | |
| CoT-8SModel=Qwen2.5-0.5B-Instruct2025.06 | 33.94 | |
| CoT-RLModel=Qwen2.5-0.5B-Instruct2025.06 | 31.92 | |
| CoAModel=Qwen2.5-0.5B-Instruct2025.06 | 28.66 |