Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Short-text generation on LCCC
Loading...
3.42
Informativeness
Belle-13B
2.8064
2.9657
3.125
3.2843
Jan 30, 2026
Informativeness
Coherence
Humanness
Updated 4d ago
Evaluation Results
Method
Method
Links
Informativeness
Coherence
Humanness
Belle-13B
Parameter scale=13B
2026.01
3.42
3.59
3.72
ChatGLM-6B
Parameter scale=6B
2026.01
3.26
3.54
3.8
HOLOEVA2.0−2.8B
Backbone=EVA2.0-2.8B,...
2026.01
3.23
3.2
3.46
HOLOBelle−13B
Backbone=Belle-13B, Pa...
2026.01
3.19
3.36
3.48
HOLOChatGLM−6B
Backbone=ChatGLM-6B, P...
2026.01
3.12
3.41
3.52
EVA2.0-2.8B
Parameter scale=2.8B
2026.01
2.83
3.22
3.08
Feedback
Search any
task
Search any
task