List your company
ResearchFormerly WizWand

Mathematical Reasoning on GSM-Symbolic Vary Both

90.22AccuracyAbstRaL
26.2642.86559.4776.075Jun 9, 2025
Updated 8mo ago

Evaluation results

MethodLinks
AbstRaLModel=Qwen2.5-Math-7B-Instruct2025.0690.220.86
AbstRaLModel=Qwen2.5-7B-Instruct2025.0688.340.74
CoT-RLModel=Qwen2.5-Math-7B-Instruct2025.0688.128.21
CoT-8SModel=Qwen2.5-Math-7B-Instruct2025.0687.667.73
CoT-8SModel=Qwen2.5-7B-Instruct2025.0687.45
AbstRaLModel=Llama-3.1-8B-Instruct2025.0686.20.92
CoT-8SModel=Llama-3.1-8B-Instruct2025.0682.365.33
AbstRaLModel=Mathstral-7B-v0.12025.0682.28-1.58
AbstRaLModel=Llama-3.2-3B-Instruct2025.0679.460.68
CoT-RLModel=Qwen2.5-7B-Instruct2025.0679.286.73
AbstRaLModel=Qwen2.5-3B-Instruct2025.0678.340.84
CoT-RLModel=Mathstral-7B-v0.12025.0676.881.44
CoT-8SModel=Mathstral-7B-v0.12025.0676.044.95
CoT-RLModel=Llama-3.1-8B-Instruct2025.0675.49.16
CoAModel=Qwen2.5-7B-Instruct2025.0674.142.45
CoAModel=Mathstral-7B-v0.12025.0674.021.31
CoT-8SModel=Qwen2.5-3B-Instruct2025.0672.5611.51
CoT-8SModel=Llama-3.2-3B-Instruct2025.0671.1415.31
CoAModel=Qwen2.5-Math-7B-Instruct2025.0669.71.83
CoAModel=Llama-3.1-8B-Instruct2025.0669.443.56
CoT-RLModel=Llama-3.2-3B-Instruct2025.0668.9813.78
CoT-RLModel=Qwen2.5-3B-Instruct2025.0668.8812.81
CoAModel=Llama-3.2-3B-Instruct2025.0667.60.59
AbstRaLModel=Qwen2.5-1.5B-Instruct2025.0664.161.29
CoAModel=Qwen2.5-3B-Instruct2025.0662.344.09
AbstRaLModel=Llama-3.2-1B-Instruct2025.0658.043.27
CoT-8SModel=Qwen2.5-1.5B-Instruct2025.0657.5212.85
CoT-RLModel=Qwen2.5-1.5B-Instruct2025.0651.268.46
CoAModel=Qwen2.5-1.5B-Instruct2025.0646.568.71
CoT-RLModel=Llama-3.2-1B-Instruct2025.0644.8821.26
AbstRaLModel=Qwen2.5-0.5B-Instruct2025.0644.56-1.27
CoAModel=Llama-3.2-1B-Instruct2025.0642.427.78
CoT-8SModel=Llama-3.2-1B-Instruct2025.0638.918.96
CoT-8SModel=Qwen2.5-0.5B-Instruct2025.0633.9810.58
CoT-RLModel=Qwen2.5-0.5B-Instruct2025.0632.287.77
CoAModel=Qwen2.5-0.5B-Instruct2025.0628.720.97