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

Reward Modeling on RewardBench v1.0 (test)

0.978Average Score

Skywork-Reward-V2-Llama-3.1-8B-40M

0.330080.498290.66650.83471Mar 6, 2025May 2, 2025Jun 28, 2025Aug 25, 2025Oct 21, 2025Dec 17, 2025Feb 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.07
0.978----
2025.07
0.964----
2025.07
0.951----
2025.07
0.95----
2025.07
0.943----
2025.07
0.939----
2025.07
0.939----
2025.07
0.938----
2025.07
0.937----
2025.07
0.934----
2025.07
0.933----
2025.07
0.931----
2025.07
0.93----
2025.07
0.929----
2025.07
0.909----
2025.07
0.904----
2025.07
0.904----
2025.07
0.903----
2025.07
0.902----
2025.07
0.899----
2025.07
0.89----
2025.07
0.885----
2025.07
0.867----
2025.07
0.857----
2025.07
0.852----
2026.02
0.8430.9410.7280.8970.804
2025.07
0.842----
2026.02
0.820.9220.6890.8720.798
2025.12
0.81480.8380.78730.88780.746
2026.02
0.8090.9110.6950.8370.794
2026.02
0.8070.9330.660.8190.816
2026.02
0.8070.9470.7650.8080.707
2026.02
0.8050.9220.7280.8230.747
2025.12
0.80310.86030.78290.89860.6705
2026.02
0.8020.9610.660.8850.703
2025.12
0.80120.8380.73460.8250.8071
2026.02
0.80.930.660.8240.787
2026.02
0.7920.9330.6620.7510.821
2025.12
0.78630.81280.73360.82430.7746
2026.02
0.7830.8970.680.730.827
2026.02
0.7810.9440.6650.7270.786
2026.02
0.7810.9440.7480.7930.638
2026.02
0.7790.9390.6840.7080.783
2026.02
0.7770.9110.6620.680.856
2025.03
0.7750.8830.5810.8070.828
2026.02
0.7710.9470.70.780.656
2025.12
0.76960.96930.49780.84190.7693
2026.02
0.7680.9220.70.8570.593
2026.02
0.7680.9530.6030.7610.756
2026.02
0.7670.9190.6290.8190.699
2026.02
0.7650.9360.6970.7850.641
2026.02
0.7640.8720.7280.780.676
2026.02
0.7640.9130.7220.7530.668
2025.03
0.7590.9650.4550.7540.862
2026.02
0.7570.9270.6380.8530.61
2026.02
0.7560.9080.7240.6870.704
2025.12
0.75240.95530.49890.81690.717
2026.02
0.7490.9330.6010.7380.725
2026.02
0.7490.9270.7060.6950.668
2025.12
0.74840.96650.45830.84050.7281
2025.03
0.7480.9220.4340.7990.837
2025.12
0.74390.95530.49780.79730.7252
2025.12
0.74150.97770.47590.81280.6997
2025.03
0.7360.9270.5420.7590.716
2025.12
0.73570.95810.3980.77970.8071
2026.02
0.730.8880.6340.7230.673
2026.02
0.7270.9160.7020.70.588
2025.12
0.72530.96090.38380.77570.7809
2025.12
0.72250.95250.40350.77970.7541
2026.02
0.7220.9390.5810.6890.68
2025.03
0.720.8550.4910.7710.765
2025.03
0.7170.8860.5640.7730.645
2025.12
0.71230.95810.3750.78650.7298
2026.02
0.7070.9110.660.6430.612
2026.02
0.7040.8880.6270.6850.616
2026.02
0.70.9080.6860.6420.566
2025.12
0.69950.93850.37720.75950.7228
2026.02
0.6990.7910.70.6530.654
2026.02
0.6940.9050.6260.5690.776
2026.02
0.6870.9250.5680.6030.651
2026.02
0.6850.9160.640.5740.611
2026.02
0.6740.9250.60.5570.615
2025.03
0.640.8240.4690.70.568
2025.03
0.5850.7770.5130.5690.482
2025.03
0.5380.6790.4230.6730.378
2025.03
0.4840.5920.290.70.355
2025.03
0.4790.5950.3580.6510.312
2025.03
0.3590.5640.2920.3850.194
2025.03
0.3550.6290.3050.120.368