Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Reasoning on VisualProbe (VP) cross-domain (test)
Loading...
0.4357
Accuracy
VIRC-7B
0.104148
0.190224
0.2763
0.362376
Dec 16, 2025
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
VIRC-7B
#Params=7B
2025.12
0.4357
VIRC-3B
#Params=3B
2025.12
0.3362
Qwen2.5-VL-7B-Instruct
#Params=7B
2025.12
0.2967
Hint-GRPO-Qwen2.5-VL-3B
#Params=3B
2025.12
0.2831
Hint-GRPO-Qwen2-VL-7B
#Params=7B
2025.12
0.2785
Qwen2.5-VL-3B-Instruct
#Params=3B
2025.12
0.2725
InternVL2.5-8B
#Params=8B
2025.12
0.2607
GPT-4o
2025.12
0.247
Qwen3-VL-8B-Instructw/ tool
#Params=8B
2025.12
0.2307
InternVL2.5-8B-MPO
#Params=8B
2025.12
0.2102
LLaVA-OV-Qwen2-7b-ov
#Params=7B
2025.12
0.207
R1-VL-7B
#Params=7B
2025.12
0.2026
MINT-CoT-7B
#Params=7B
2025.12
0.1784
DeepSeek-VL2
#Params=4.5B
2025.12
0.1712
MM-Eureka
#Params=7B
2025.12
0.1169
Feedback
Search any
task
Search any
task