Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Scientific Text Generation on VTechAGP PLOS 1.0 (test)
Loading...
15.89
ROUGE-2
Sci-LoRA
5.7188
8.3594
11
13.6406
May 24, 2025
ROUGE-2
s-BLEU
COMET
FRES
Updated 4d ago
Evaluation Results
Method
Method
Links
ROUGE-2
s-BLEU
COMET
FRES
Sci-LoRA
2025.05
15.89
4.06
80.29
44.36
Phi-4
2025.05
15.8
4.58
80.05
33.54
Qwen2.5
2025.05
13.25
3.23
79.9
43.43
Mixtral
2025.05
11.26
2.58
79.26
49.15
OPT
2025.05
10.91
-
77.73
34.26
GPT-3.5
2025.05
10.5
2.58
79.69
41.8
GPT-4o
2025.05
9.81
2.12
80.26
42
Mistral
2025.05
6.75
1.42
78.45
53.1
LLaMA3
2025.05
6.11
1.35
77.43
50.57
Feedback
Search any
task
Search any
task