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

Citation and Evidence Recall on MuSiQue

80.2Rk

GPT-5.2

7.19226.14645.164.054Oct 23, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
80.268.687
2025.10
73.264.580.5
2025.10
70.410070.4
2025.10
66.263.874.2
2025.10
64.736.375.4
2025.10
62.554.476.1
2025.10
61.55070.1
2025.10
57.851.369.7
2025.10
54.950.468
2025.10
51.148.363.3
2025.10
48.710048.7
2025.10
44.736.454.3
2025.10
4434.763.2
2025.10
41.221.853.5
2025.10
41.129.649.1
2025.10
39.124.746
2025.10
31.829.740.9
2025.10
31.326.744
2025.10
30.51.150
2025.10
1011.514.1