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

Instruction Following on Alpaca

5.27Speedup (x)

EAGLE3 + DM

2.03562.87533.7154.5547Jan 9, 2026Feb 1, 2026Feb 24, 2026Mar 19, 2026Apr 11, 2026May 4, 2026May 28, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.02
5.2752------7.74----------
2026.02
5.0256------7.25----------
2026.02
4.9250.6------6.89----------
2026.02
4.7551.3------6.59----------
2026.03
4.53---7.31--------------
2026.02
4.4755------6.3----------
2026.03
4.4---7.01--------------
2026.02
4.3150------5.83----------
2026.05
4.2----7.12-------------
2026.01
4.13-----5.89------------
2026.05
4.13----6.83-------------
2026.05
4.06----7.09-------------
2026.01
4.04----6.51-------------
2026.01
3.98-----9.24------------
2026.03
3.98---6--------------
2026.01
3.94----6.36-------------
2026.01
3.92----6.93-------------
2026.01
3.84-----5.48------------
2026.01
3.84-----10.24------------
2026.05
3.79----6.54-------------
2026.01
3.78----6.61-------------
2026.01
3.71----6.56-------------
2026.05
3.69----6.28-------------
2026.05
3.67----6.52-------------
2026.03
3.65-------6.2----------
2026.03
3.61-------6.01----------
2026.05
3.57----5.96-------------
2026.05
3.56-------4.7----------
2026.05
3.54-------4.68----------
2026.05
3.53-------4.64----------
2026.01
3.51-----8.15------------
2026.03
3.51-------5.12----------
2026.01
3.46----5.18-------------
2026.03
3.46-------5.79----------
2026.05
3.46-------4.64----------
2026.03
3.43-------5.68----------
2026.03
3.43-------5----------
2026.03
3.42-------5.51----------
2026.03
3.4-------5.49----------
2026.03
3.39-------4.95----------
2026.03
3.38-------5.47----------
2026.03
3.38-------4.59----------
2026.03
3.36-------5.51----------
2026.04
3.36---5.09--------------
2026.01
3.35-----8.31------------
2026.03
3.34-------5.39----------
2026.04
3.32---5.35--------------
2026.03
3.3-------5.18----------
2026.03
3.27-------5.54----------
2026.03
3.24-------5.47----------
2026.01
3.23----5.64-------------
2026.04
3.23---4.97--------------
2026.03
3.21-------5.39----------
2026.04
3.2---4.89--------------
2026.03
3.19-------4.95----------
2026.01
3.15-----7.82------------
2026.01
2.94-----8.24------------
2026.01
2.86-----8.71------------
2026.03
2.83-------4.76----------
2026.05
2.8-------3.88----------
2026.03
2.79-------4.53----------
2026.05
2.78-------3.87----------
2026.03
2.76-------4.83----------
2026.01
2.71---2.89--------------
2026.01
2.66---2.71--------------
2026.01
2.66-----7.71------------
2026.01
2.64-----5.3------------
2026.05
2.59-------3.52----------
2026.05
2.52-------3.46----------
2026.04
2.46---3.55--------------
2026.01
2.45---2.65--------------
2026.05
2.45-------2.15----------
2026.01
2.44---2.66--------------
2026.01
2.44---2.64--------------
2026.01
2.44----3.39-------------
2026.01
2.43---2.64--------------
2026.04
2.43---3.51--------------
2026.05
2.41----2.93-------------
2026.05
2.41-------2.16----------
2026.01
2.4----3.51-------------
2026.03
2.38---2.85--------------
2026.01
2.37---2.59--------------
2026.01
2.35---2.48--------------
2026.05
2.33----3.34-------------
2026.05
2.29----3.56-------------
2026.05
2.28-------3.15----------
2026.05
2.25----2.76-------------
2026.03
2.24---2.87--------------
2026.01
2.23-----4.61------------
2026.05
2.23-------3.1----------
2026.05
2.21-------3.12----------
2026.05
2.21-------2.84----------
2026.05
2.19----3.32-------------
2026.05
2.18-------3.03----------
2026.05
2.18-------2.84----------
2026.05
2.17----3.06-------------
2026.01
2.16-----4.22------------
2026.03
2.16-------2.59----------
2026.05
2.16-------2.78----------
2026.05
2.16-------2.78----------
Showing 100 of 340 rows