Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-turn Dialogue on MTBench101

9.03Score

Full-Context

2.48844.18675.8857.5833Jan 29, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
9.03
2026.01
8.43
2026.01
8.3
2026.01
8.11
2026.01
6.42
2026.01
6.32
2026.01
6
2026.01
5.61
2026.01
5.06
2026.01
5.04
2026.01
5.02
2026.01
5
2026.01
5
2026.01
4.98
2026.01
4.88
2026.01
4.84
2026.01
4.76
2026.01
4.74
2026.01
4.74
2026.01
4.71
2026.01
4.31
2026.01
4.21
2026.01
4.11
2026.01
3.93
2026.01
3.93
2026.01
3.92
2026.01
3.92
2026.01
3.77
2026.01
3.66
2026.01
3.62
2026.01
3.58
2026.01
3.21
2026.01
2.74