List your company

Mathematical Word Problem Solving on SVAMP (Robustness Metrics)

100Accuracy under AttackReporting-and-penalty mechanism
49.0462.2775.588.73Apr 26, 2026

Evaluation results

MethodLinks
Reporting-and-penalty mechanismAttack Type=All Attack Types, LLM Model=All Above Models2026.04100100
GroupGuardAttack Type=False Consensus, LLM Model=Deepseek-V3.12026.045598
GroupGuardAttack Type=False Consensus, LLM Model=Qwen3-32B2026.045283
GroupGuardAttack Type=False Consensus, LLM Model=Qwen3-235B2026.045177