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

Instruction Following on EQ-Bench Longform (ID prompts) (45 prompts)

1,911Elo Score

GPT-5.4

755.561,055.531,355.51,655.47Jun 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
1,911
2026.06
1,774
2026.06
1,728
2026.06
1,658
2026.06
1,619
2026.06
1,612
2026.06
1,563
2026.06
1,505
2026.06
1,494
2026.06
1,451
2026.06
1,343
2026.06
1,301
2026.06
1,214
2026.06
1,033
2026.06
1,011
2026.06
800