Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Mathematical Reasoning on GEOQA-8k (test)
Loading...
59.95
Accuracy
DGPO
38.9836
44.4268
49.87
55.3132
Jan 28, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
DGPO
Backbone=Qwen2.5-VL-3B...
2026.01
59.95
GPG
Backbone=Qwen2.5-VL-3B...
2026.01
59.02
DAPO
Backbone=Qwen2.5-VL-3B...
2026.01
59.02
GRPO-AD
Backbone=Qwen2.5-VL-3B...
2026.01
58.09
Dr.GRPO
Backbone=Qwen2.5-VL-3B...
2026.01
57.96
GRPO
Backbone=Qwen2.5-VL-3B...
2026.01
57.43
GSPO
Backbone=Qwen2.5-VL-3B...
2026.01
57.16
Base Model
Backbone=Qwen2.5-VL-3B...
2026.01
39.79
Feedback
Search any
task
Search any
task