Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-Ended Question Answering on AGMMU Open-Ended (test)
Loading...
43
BLEU-4
AgriChat
7.64
16.82
26
35.18
Mar 14, 2026
BLEU-4
ROUGE-2
METEOR
BERTScore
LongCLIP
T5 Cos
SBERT
LLM Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU-4
ROUGE-2
METEOR
BERTScore
LongCLIP
T5 Cos
SBERT
LLM Judge Score
AgriChat
Model Scale=7B
2026.03
43
2.83
13.44
82.81
75.08
49.95
39.23
46.93
LLaVA-OneVision
Model Scale=7B
2026.03
35
2.6
12.45
83.74
75.91
47.17
39.65
52.49
Llama-3.2
Model Scale=11B
2026.03
11
1.04
7.69
80.24
75.68
44.4
36.3
55.7
Qwen-2.5
Model Scale=7B
2026.03
9
0.76
6.62
80.07
75.72
43.47
36.82
59.93
Feedback
Search any
task
Search any
task