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

Multi-agent Question Answering on CommonsenseQA (first 300 questions)

64.44Average Accuracy

TextFullT

24.576834.925945.27555.6241May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
64.4466.33505.035.47
2026.05
63.7864.3372.011.47
2026.05
5656.33570.7
2026.05
50.22521,137.8911.58
2026.05
49.5653.331,247.513.15
2026.05
4850.67960.2610.04
2026.05
47.7850.331,717.618.18
2026.05
47.22491,316.214.48
2026.05
43.6743.67113.591.25
2026.05
26.1126324.433.61