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

Correctness Evaluation on PPE Correctness (test)

87.2Score

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

58.0865.6473.280.76Jul 2, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
87.2--
83.4--
75.1--
74.7--
2025.07
73.7--
2025.07
72.9--
72.1--
70.5--
2025.07
69.2--
68.3--
67.4--
2025.07
67.1--
2025.07
64.4--
2025.07
64.1--
2025.07
63.9--
2025.07
63.2--
2025.07
63.2--
2025.07
63--
2025.07
62.5--
2025.07
61.9--
2025.07
61.9--
2025.07
60.6--
2025.07
60.4--
2025.07
59.2--
2025.12
-0.19310.1597
2025.12
-0.32120.2978
2025.12
-0.31970.294
2025.12
-0.06430.0684
2025.12
-0.14620.152
2025.12
-0.09320.098
2025.12
-0.0990.1034
2025.12
-0.06890.1193