List your company

Commonsense Reasoning on StrategyQA (Robustness and Latency)

51.67Accuracy (Clean)AGLS
25.6732.4239.1745.92May 26, 2025

Evaluation results

MethodLinks
AGLSModel=gemma2-2B2025.0551.6736.6729.030.26
AGLSModel=llama3.3-70B2025.0550.3347.335.961.49
AGLSModel=llama3.1-70B2025.0549.67475.382.03
AGLSModel=qwen2.5-0.5B2025.0526.6725.335.021.09