Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Understanding on HR-Bench 8K
Loading...
86.6
Avg@8 Exact Match
SenseNova-MARS-32B
58.52
65.81
73.1
80.39
Dec 30, 2025
Avg@8 Exact Match
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@8 Exact Match
SenseNova-MARS-32B
Method Category=Agenti...
2025.12
86.6
Gemini-2.5-Pro
Method Category=Direct...
2025.12
85.4
Qwen3-VL-235B-A22B-Instruct
Method Category=Agenti...
2025.12
82.4
Qwen3-VL-32B-Instruct
Method Category=Agenti...
2025.12
81.6
Skywork-R1V4
Method Category=Agenti...
2025.12
79.8
SenseNova-MARS-8B
Method Category=Agenti...
2025.12
78.4
Qwen3-VL-8B-Instruct
Method Category=Direct...
2025.12
74.6
DeepEyesV2
Method Category=Agenti...
2025.12
73.8
Mini o3
Method Category=Agenti...
2025.12
73.3
Thyme
Method Category=Agenti...
2025.12
72
DeepEyes
Method Category=Agenti...
2025.12
69.5
Monet
Method Category=Agenti...
2025.12
68
Pixel-Reasoner
Method Category=Agenti...
2025.12
66.1
Qwen2.5-VL-32B-Instruct
Method Category=Direct...
2025.12
63.6
Qwen2.5-VL-7B-Instruct
Method Category=Direct...
2025.12
62.1
LLaVA-onevison
Method Category=Direct...
2025.12
59.8
GPT-4o
Method Category=Direct...
2025.12
59.6
Feedback
Search any
task
Search any
task