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

Open-ended Text Generation on MT-Bench

4.88MT-1 Score

DECA

3.88164.14084.44.6592Jun 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
4.88-3.34.1
2026.06
4.87-3.264.06
2026.06
4.5-2.933.72
2026.06
4.43-2.953.69
2026.06
4.31-33.65
2026.06
4.3-2.873.59
2026.06
4.18-2.653.41
2026.06
3.92-2.623.27
2026.01
-3.7--
2026.01
-2.2--
2026.01
-2.8--
2026.01
-3.3--