Share your thoughts, 1 month free Claude Pro on usSee more

Hybrid Reasoning on MATH_MIX (test)

88Accuracy

Agent-GWO

Updated 1mo ago

Evaluation Results

Method	Links
Agent-GWO 2026.04		88
Agent-GWO 2026.04		87.5
AoT 2026.04		86.9
ToT 2026.04		85.6
AFlow 2026.04		85.3
GoT 2026.04		84.4
AoT 2026.04		84
Self-Refine 2026.04		83.8
Agent-GWO 2026.04		83.5
ToT 2026.04		83.5
AFlow 2026.04		82.6
GoT 2026.04		82.4
CoT-SC/n=5 2026.04		81.6
CoT 2026.04		80.1
Self-Refine 2026.04		79.6
AoT 2026.04		78.8
ToT 2026.04		77.8
AFlow 2026.04		77
CoT-SC/n=5 2026.04		77
GoT 2026.04		76.8
CoT 2026.04		75.1
Self-Refine 2026.04		74.6
CoT-SC/n=5 2026.04		73.9
CoT 2026.04		70.4