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

Chat & Instruction Following on Arena-Hard V2 (Accuracy)

72.8Accuracy

Super

68.43269.56670.771.834Jul 5, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
72.8
2026.07
72.6
2026.07
69
2026.07
68.6