List your company
ResearchFormerly WizWand

Mathematical Reasoning on GSM-Symbolic Vary Name

92.48AccuracyAbstRaL
28.124844.832461.5478.2476Jun 9, 2025
Updated 8mo ago

Evaluation results

MethodLinks
AbstRaLModel=Qwen2.5-7B-Instruct2025.0692.48
CoT-8SModel=Qwen2.5-7B-Instruct2025.0692.3
CoT-RLModel=Qwen2.5-Math-7B-Instruct2025.0691.54
CoT-8SModel=Qwen2.5-Math-7B-Instruct2025.0691.08
AbstRaLModel=Qwen2.5-Math-7B-Instruct2025.0690.14
CoT-8SModel=Llama-3.1-8B-Instruct2025.0687.46
CoT-RLModel=Llama-3.1-8B-Instruct2025.0687.1
AbstRaLModel=Llama-3.1-8B-Instruct2025.0686.72
AbstRaLModel=Mathstral-7B-v0.12025.0682.14
CoT-RLModel=Qwen2.5-7B-Instruct2025.0681.7
CoT-8SModel=Mathstral-7B-v0.12025.0680.84
CoT-RLModel=Mathstral-7B-v0.12025.0679.86
AbstRaLModel=Llama-3.2-3B-Instruct2025.0679.82
AbstRaLModel=Qwen2.5-3B-Instruct2025.0678.52
CoT-8SModel=Qwen2.5-3B-Instruct2025.0678.2
CoAModel=Mathstral-7B-v0.12025.0677.4
CoT-RLModel=Qwen2.5-3B-Instruct2025.0677.06
CoT-8SModel=Llama-3.2-3B-Instruct2025.0676.38
CoT-RLModel=Llama-3.2-3B-Instruct2025.0675.16
CoAModel=Qwen2.5-7B-Instruct2025.0674.08
CoAModel=Llama-3.1-8B-Instruct2025.0670.86
CoAModel=Qwen2.5-Math-7B-Instruct2025.0669.76
CoAModel=Llama-3.2-3B-Instruct2025.0668.02
CoT-8SModel=Qwen2.5-1.5B-Instruct2025.0664.16
AbstRaLModel=Qwen2.5-1.5B-Instruct2025.0664.14
CoAModel=Qwen2.5-3B-Instruct2025.0661.34
AbstRaLModel=Llama-3.2-1B-Instruct2025.0658.38
CoT-RLModel=Qwen2.5-1.5B-Instruct2025.0658.3
CoT-RLModel=Llama-3.2-1B-Instruct2025.0653.42
CoAModel=Qwen2.5-1.5B-Instruct2025.0649.42
AbstRaLModel=Qwen2.5-0.5B-Instruct2025.0644.16
CoAModel=Llama-3.2-1B-Instruct2025.0643.72
CoT-8SModel=Llama-3.2-1B-Instruct2025.0642.5
CoT-RLModel=Qwen2.5-0.5B-Instruct2025.0639.48
CoT-8SModel=Qwen2.5-0.5B-Instruct2025.0637.24
CoAModel=Qwen2.5-0.5B-Instruct2025.0630.6