Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scientific Multimodal MCQA on MAC
Loading...
82.26
Accuracy
SCICON
41.232
51.8835
62.535
73.1865
Mar 30, 2026
Accuracy
F1 Score
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
SCICON
Backbone=Qwen 3.5 9B
2026.03
82.26
82.34
VCD
Backbone=Qwen 3.5 9B
2026.03
81.96
81.92
Greedy
Backbone=Qwen 3.5 9B
2026.03
81.35
81.4
ICD
Backbone=Qwen 3.5 9B
2026.03
81.04
81.01
SCICON
Backbone=Qwen 3.5 4B
2026.03
74.01
74.24
Greedy
Backbone=Qwen 3.5 4B
2026.03
69.72
70.75
VCD
Backbone=Qwen 3.5 4B
2026.03
68.5
68.77
ICD
Backbone=Qwen 3.5 4B
2026.03
58.41
58.57
SCICON
Backbone=Phi-3.5-visio...
2026.03
49.54
49.89
VCD
Backbone=Phi-3.5-visio...
2026.03
43.73
43.27
Greedy
Backbone=Phi-3.5-visio...
2026.03
42.81
42.02
ICD
Backbone=Phi-3.5-visio...
2026.03
42.81
41.6
Feedback
Search any
task
Search any
task
