Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text Generation on TM4K
Loading...
45.79
BLEU-1
EyExIn
24.834
30.2745
35.715
41.1555
Mar 7, 2026
BLEU-1
ROUGE-L
METEOR
BERT-F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU-1
ROUGE-L
METEOR
BERT-F1
EyExIn
Fine-tuned=true
2026.03
45.79
35.52
43.16
94.66
Qwen2.5-VL
Fine-tuned=true
2026.03
41.23
30.46
40.76
94.2
LLaVA
Fine-tuned=true
2026.03
38.54
26.88
36.92
93.87
Qwen3-VL-Max
2026.03
36.23
20.82
32.58
93.52
ChatGPT-5.2
2026.03
29.42
20.98
27.26
93.2
Gemini3-Pro
2026.03
25.64
21.3
30.56
92.86
Feedback
Search any
task
Search any
task