List your company

Question Generation on EduMath-CQ

47.11Win RateEQPR
26.195631.625337.05542.4847Jun 1, 2025

Evaluation results

MethodLinks
EQPRBackbone=Claude-3.52025.0647.1145.92——————
EQPRBackbone=DeepSeek-V32025.0646.2343.11—20.3346.8644.5771.0291.73
REACTBackbone=Claude-3.52025.0645.2741.26——————
DEARBackbone=Claude-3.52025.0644.1934.75——————
EQPRBackbone=GPT-4o2025.0644.0743.43——————
REACTBackbone=GPT-4o2025.0642.6840.72——————
DEARBackbone=DeepSeek-V32025.0641.8137.88—20.7149.0642.1174.4892.59
COT-BONBackbone=Claude-3.52025.0641.6138.37——————
DEARBackbone=GPT-4o2025.0641.339.59——————
EQPRBackbone=GPT-4o-Mini2025.0639.9235.81—24.852.748.1370.8990.63
REACTBackbone=DeepSeek-V32025.0639.7538.91—21.7647.9847.0670.3290.64
COT-BONBackbone=DeepSeek-V32025.0638.9929.63—13.5843.628.9370.8590.25
REACTBackbone=GPT-4o-Mini2025.0638.433.66—18.953.236.7272.5589.32
COTBackbone=DeepSeek-V32025.0638.231.45—12.1142.922.5170.6490.84
COTBackbone=GPT-4o2025.0638.1634.78——————
COTBackbone=Claude-3.52025.0637.9532.08——————
EQPRBackbone=DeepSeek-V32025.0636.67—1.93—————
COTBackbone=GPT-4o-Mini2025.0635.7827.88—11.629.6424.4568.5290.12
DEARBackbone=GPT-4o-Mini2025.0635.1827.35—13.3123.0921.7470.3485.77
REACTBackbone=DeepSeek-V32025.0635—1.87—————
COT-BONBackbone=GPT-4o-Mini2025.0634.521.25—8.5222.5910.5669.1990.23
COT-BONBackbone=GPT-4o2025.0634.3436.58——————
COT-BONBackbone=DeepSeek-V32025.0633.67—1.78—————
DEARBackbone=DeepSeek-V32025.0631—1.84—————
COTBackbone=DeepSeek-V32025.0627—1.83—————