Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Object-Counting on Extreme Illumination Triplet Instruct-Following Dataset
Loading...
74.66
Accuracy
Ours-7B
54.0784
59.4217
64.765
70.1083
Mar 29, 2026
Accuracy
MAE
Updated 2mo ago
Evaluation Results
Method
Method
Links
Accuracy
MAE
Ours-7B
MLLM Type=Event-Enhanc...
2026.03
74.66
0.4557
Baseline-7B
MLLM Type=Event-Enhanc...
2026.03
72.73
0.5303
InternVL
MLLM Type=General Model
2026.03
72.56
0.8641
Ours-3B
MLLM Type=Event-Enhanc...
2026.03
71.08
0.6127
Baseline-3B
MLLM Type=Event-Enhanc...
2026.03
69.66
0.6655
LLaVA-7B
MLLM Type=General Model
2026.03
67.84
0.9957
EventGPT
MLLM Type=Event-specia...
2026.03
67.41
1.0015
Q-Instruct
MLLM Type=Illumination...
2026.03
66.87
0.9803
Deepseek-VL
MLLM Type=General Model
2026.03
54.87
1.0544
Feedback
Search any
task
Search any
task