Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Idiom-based vision-language matching (Subtask B) on AdMIRe multilingual (15 languages) 2.0 (test)
Loading...
32
Top-1 Acc
Best submission
5.688
12.519
19.35
26.181
Feb 20, 2026
Top-1 Acc
Updated 5mo ago
Evaluation Results
Method
Method
Links
Top-1 Acc
Best submission
System architecture=Si...
2026.02
32
Ensemble (Qwen3+GPT-4o)
System architecture=Qw...
2026.02
29
GPT-4o
2026.02
28
Qwen3-32B
2026.02
26.5
Mistral-large
2026.02
25.5
Llama3.1-70B
2026.02
25
DeepSeek-v3
2026.02
23.5
CLIP baseline
System architecture=XL...
2026.02
6.7
Feedback
Search any
task
Search any
task