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

Multi-turn dialogue on MT-Eval

8.16LLM-EVAL Score

MDS

7.7967.89057.9858.0795Apr 9, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.04
8.167.5258.40.8571.25
2026.04
8.168.2659.30.8481.25
2026.04
8.097.4156.70.8455.67
2026.04
8.087.4456.80.8464.92
2026.04
8.067.42570.8455.58
2026.04
8.057.2156.70.8456
2026.04
8.057.48570.8454.58
2026.04
8.058.1857.90.8454.75
2026.04
8.047.4456.90.8315
2026.04
8.017.4356.80.8455.5
2026.04
8.018.258.10.8475.33
2026.04
87.4155.80.8426.92
2026.04
88.155.30.8285.67
2026.04
7.997.2356.20.8387
2026.04
7.988.1256.40.8416.17
2026.04
7.968.0555.80.8445.58
2026.04
7.928.2158.50.854.67
2026.04
7.918.0857.50.8465.75
2026.04
7.98.0856.80.8437.25
2026.04
7.817.949.60.8267.25