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

End-to-end Question Answering on MuSiQue (test val)

10.79EM

SetR-CoT & IRI

5.076.5558.049.525Jul 9, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.07
10.7915.43
2025.07
10.3815.28
2025.07
9.7614.31
2025.07
9.4313.25
2025.07
8.0612.5
2025.07
8.0211.07
2025.07
8.0211.72
2025.07
7.7811.35
2025.07
7.6111.77
2025.07
7.4410.78
2025.07
7.0310.87
2025.07
6.919.98
2025.07
6.7810.03
2025.07
6.6210.57
2025.07
6.5310.64
2025.07
6.1210
2025.07
6.049.26
2025.07
5.999.03
2025.07
5.468.22
2025.07
5.298.42