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

Long-context Language Modeling on LongBench v2

29.62Accuracy

FoLoRA

27.758428.241728.72529.2083May 28, 2026
Updated 17h ago

Evaluation Results

MethodLinks
2026.05
29.62-------
2026.05
29.42-------
2026.05
29.42-------
2026.05
29.22-------
2026.05
29.02-------
2026.05
29.02-------
2026.05
28.82-------
2026.05
28.03-------
2026.05
28.03-------
2026.05
28.03-------
2026.05
27.83-------
2026.05
27.83-------
2025.12
-3.11.52.60.88.97.23.1
2025.12
-4.22.72.13.59.68.54.1
2025.12
-2017.68.62.61611.814.9
2025.12
-18.115.223.116.218.319.218.1
2025.12
-2014.425.9182221.219.5
2025.12
-22.919.227.225.62424.223.1
2025.12
-22.319.612.38.513.220.118.1
2025.12
-29.527.228.629.115.327.927.9
2025.12
-34.318.429.630.81633.328.3
2025.12
-34.925.633.338.52233.331.9