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

Search-based Question Answering on SearchQA

42Hotpot Score

HarnessForge

28.136831.735935.33538.9341Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
424242
2026.06
41.334241.67
2026.06
41.3344.3342.83
2026.06
40.6741.3341
2026.06
4039.3339.67
2026.06
36.6738.6737.67
2026.06
3643.3339.67
2026.06
35.334037.67
2026.06
32.6730.6731.67
2026.06
323232
2026.06
31.332829.67
2026.06
31.333231.67
2026.06
31.3332.6732
2026.06
30.6729.3330
2026.06
30.673030.33
2026.06
29.333029.67
2026.06
29.333029.5
2026.06
28.672828.33