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

Commonsense Reasoning on Commonsense Reasoning Suite (test)

0.9594HellaSwag Accuracy

PERA (r = 16)

-0.0382720.2207390.479750.738761May 23, 2025Jul 25, 2025Sep 27, 2025Nov 29, 2025Feb 1, 2026Apr 5, 2026Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
0.95940.8738-0.88570.93730.8362--0.886-0.89270.76150.8316-
2026.04
0.95610.8712-0.89830.93560.8353--0.884-0.88950.75540.8158-
2026.04
0.9550.852-0.8930.9050.804--0.858-0.8560.7460.799-
2026.04
0.95380.8829-0.89610.96170.8891--0.918-0.89340.73060.8204-
2026.04
0.95360.8672-0.8970.93270.829--0.8832-0.8770.7540.8115-
2026.04
0.94850.8608-0.89120.93060.8259--0.874-0.86740.73850.8106-
2026.04
0.9350.828-0.8670.8770.757--0.828-0.8480.7230.793-
2026.04
0.9230.854-0.8830.9540.887--0.88-0.810.690.808-
2026.04
0.9170.8079-0.8520.8420.712--0.79-0.8430.7080.799-
2026.04
0.8910.7969-0.8370.8370.682--0.824-0.8260.7180.76-
2026.04
0.88980.8214-0.84390.87790.7329--0.832-0.86270.7370.7953-
2026.04
0.88660.8261-0.85310.88550.7355--0.854-0.87130.71830.8035-
2026.04
0.88120.8142-0.83350.86740.7381--0.846-0.83980.71220.7953-
2026.04
0.8360.7761-0.7990.7980.647--0.81-0.8260.6980.795-
2025.12
0.81050.714-0.82260.80930.5392--0.442-0.7380.8364--
2025.05
0.81--0.84------0.62--0.95
2026.04
0.7860.738-0.7360.8590.717--0.744-0.7580.60.7-
2026.04
0.7850.7701-0.8540.8980.799--0.748-0.6610.7310.685-
2025.12
0.76640.6582-0.76610.76140.4573--0.414-0.6930.7498--
2026.06
0.76020.6436-0.79110.7630.4633--0.442-0.69140.77710.4606-
2026.06
0.73690.6316-0.77150.72560.4445--0.42-0.69140.78690.4759-
2026.06
0.73640.6263-0.77090.73020.448--0.43-0.68820.7330.4734-
2026.06
0.7260.6088-0.77480.7340.4104--0.414-0.64010.71960.4514-
2026.06
0.72530.6084-0.78020.73270.4283--0.406-0.6290.71250.4529-
2026.02
0.71730.7418-0.7880.8780.752--0.7847-0.64530.67870.69-
2025.05
0.71--0.77------0.66--0.82
2025.05
0.71--0.82------0.61--0.89
2026.06
0.69730.5948-0.75950.69320.3951--0.4-0.64480.73550.433-
2026.02
0.68930.7205-0.77270.8620.7213--0.754-0.64070.66270.6613-
2026.02
0.68330.7148-0.790.850.7273--0.7667-0.60330.64270.6553-
2025.05
0.68--0.78------0.7--0.92
2025.05
0.68--0.72------0.57--0.92
2026.06
0.67660.572-0.72420.65280.3891--0.396-0.67090.62940.4371-
2026.06
0.66640.5844-0.73180.65280.3805--0.392-0.66850.72630.4565-
2025.05
0.66--0.74------0.55--0.92
2026.02
0.65730.7233-0.8040.8760.7473--0.7707-0.61470.6380.6787-
2026.06
0.65720.5678-0.73780.66580.3549--0.398-0.60460.69240.4319-
2026.02
0.64930.7115-0.77730.84670.7153--0.7487-0.64670.64270.6653-
2026.02
0.64930.7194-0.7880.85930.7427--0.7433-0.60530.66870.6987-
2025.12
0.64670.5551-0.71760.52950.3439--0.346-0.6440.6581--
2026.06
0.63150.5377-0.74270.63260.349--0.37-0.54620.61870.411-
2025.05
0.62--0.77------0.6--0.8
2025.12
0.61190.5037-0.68990.49280.343--0.32-0.63690.4315--
2026.06
0.6030.5307-0.71820.61410.3558--0.366-0.56670.62870.393-
2026.06
0.58760.5331-0.66920.54460.3413--0.332-0.64090.71220.4365-
2025.12
0.58060.5772-0.68990.670.3763--0.386-0.65190.6859--
2025.05
0.58--0.83------0.62--0.96
2026.06
0.57870.5354-0.70780.58080.3114--0.356-0.60220.72810.4181-
2026.02
0.57730.688-0.79070.85530.7327--0.7387-0.54130.6480.62-
2026.06
0.54830.5093-0.71380.59760.3106--0.36-0.52960.60280.4115-
2025.05
0.53--0.65------0.4--0.74
2026.06
0.52810.4992-0.70890.57280.2986--0.342-0.52330.62140.3987-
2025.05
0.52--0.84------0.56--0.95
2026.06
0.48660.469-0.64740.48910.2841--0.328-0.53510.60210.3792-
2026.06
0.47660.4691-0.5620.48270.3473--0.36-0.54220.57740.4048-
2026.06
0.47360.4494-0.64690.49160.2935--0.316-0.53590.46420.3736-
2026.06
0.47360.4491-0.64470.49160.2935--0.316-0.53590.46420.3736-
2026.06
0.47130.4641-0.61810.44910.2918--0.298-0.57220.6220.39-
2025.05
0.47--0.63------0.54--0.71
2026.06
0.44520.4397-0.55220.4520.3294--0.354-0.40380.57740.4038-
2025.12
0.44450.432-0.64130.30960.2364--0.312-0.52210.5587--
2026.06
0.43990.4512-0.55170.45330.3089--0.362-0.53670.55870.3982-
2026.04
0.43530.7863-0.87430.91160.7961--0.856-0.86740.74280.8071-
2026.06
0.42930.46-0.65070.49490.2637--0.31-0.52570.61710.3884-
2025.12
0.40520.4457-0.59110.44810.2477--0.314-0.56160.5524--
2025.05
0.4--0.54------0.51--0.54
2026.06
0.39730.4215-0.53210.41120.2927--0.332-0.53280.54530.3291-
2026.01
0.3660.4620.3540.6540.5840.2640.630.3660.3260.5750.520.44--
2026.01
0.3640.4770.3840.650.5780.2760.660.30.3120.5860.5480.584--
2026.01
0.3620.4450.3760.6420.5860.2740.640.3240.3360.6040.5320.546--
2026.06
0.35460.4517-0.65510.49710.2662--0.308-0.5130.62170.3976-
2026.01
0.3520.4440.3620.6460.5860.2720.630.2360.3040.5860.4920.416--
2026.04
0.29090.7246-0.80790.85310.7142--0.812-0.80190.72170.7953-
2026.01
0.280.4240.2780.590.4140.230.540.2880.2540.5350.50.608--
2026.01
0.2740.4230.2820.5640.4280.2440.530.350.2560.5340.50.544--
2026.01
0.270.4110.290.6040.4280.2180.550.3180.2380.5930.4920.374--
2026.01
0.2640.4220.2840.6080.4280.2240.60.230.2480.5530.5040.544--
2025.05
0.25--0.76------0.45--0.87
2025.05
0.24--0.76------0.44--0.9
2025.05
0.24--0.58------0.47--0.6
2025.05
0.23--0.73------0.43--0.9
2026.04
0.14010.3696-0.45050.32740.3157--0.292-0.50120.56850.3613-
2025.05
0.14--0.4------0.38--0.16
2025.05
0.07--0.72------0.49--0.91
2026.04
0.06910.2129-0.12350.08630.0606--0.094-0.40570.55930.305-
2026.04
0.01770.1811-0.11640.08630.0742--0.096-0.37650.59970.0819-
2026.04
0.00010.1224-0.36020.01980.0017--0.008-00.58750.002-