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

Factuality-based Question Answering on FreshQA 2025/11/24

44C

Base

7.617.0526.535.95Feb 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
4444128850---
2026.02
4456--44---
2026.02
38.427.65.428.66658.287.769.9
2026.02
37.444.817.882.245.5---
2026.02
36.427729.663.457.483.968.2
2026.02
3627.86.829.463.856.484.167.5
2026.02
35.847.2178343.1---
2026.02
35.638.64.421.474.2488962.4
2026.02
35.629.6727.865.254.683.666
2026.02
35.2247.633.259.259.582.269
2026.02
35.224.67.632.659.858.982.268.6
2026.02
3536.25.223.671.249.287.162.8
2026.02
34.658.27.292.837.3---
2026.02
34.238.63.823.472.8479061.7
2026.02
33.466.6--33.4---
2026.02
32.261.66.293.834.3---
2026.02
31.435.86.226.667.246.783.559.9
2026.02
28.829.66.435.258.449.381.861.5
2026.02
28.633.46.831.26246.180.858.7
2026.02
28.433.68.229.86245.877.657.6
2026.02
28347.630.46245.278.757.4
2026.02
2854.617.482.633.9---
2026.02
26.41517.241.441.463.860.562.1
2026.02
26.212.816.644.43967.261.264.1
2026.02
25.820.812.44146.655.467.560.9
2026.02
25.6277.44052.648.777.659.8
2026.02
25.419.8945.845.256.273.863.8
2026.02
24.423.68.443.64850.874.460.4
2026.02
24.424.49.24248.85072.659.2
2026.02
23.62010.44643.654.169.460.8
2026.02
23.627.610.83851.246.168.655.1
2026.02
23.218.810484255.269.961.7
2026.02
2323.29.444.446.249.87158.5
2026.02
21.621.412.444.64350.263.556.1
2026.02
19.829.67.64349.440.172.351.6
2026.02
19.414.81451.834.256.758.157.4
2026.02
18.821.69.450.240.446.566.754.8
2026.02
17.819.811.45137.647.36153.3
2026.02
17.413.414.454.830.856.554.755.6
2026.02
9818651752.933.340.9