Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Real-World Understanding on HRBench 4K (Score)
Loading...
86.9
Score
Gemini 2.5 Pro
59.548
66.649
73.75
80.851
Nov 7, 2025
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Gemini 2.5 Pro
Tool=Code, Param Size=-
2025.11
86.9
DeepEyesV2
Tool=General, Param Si...
2025.11
77.9
Thyme
Tool=Code, Param Size=7B
2025.11
77
DeepEyes
Tool=Crop, Param Size=7B
2025.11
75.1
Qwen2.5-VL
Tool=✗, Param Size=32B
2025.11
74.1
Pixel-Reasoner
Tool=Crop, Param Size=7B
2025.11
74
Qwen2.5-VL
Tool=✗, Param Size=7B
2025.11
71.6
InternVL3
Tool=✗, Param Size=8B
2025.11
70
LLaVA-OV
Tool=✗, Param Size=7B
2025.11
63
GPT-4o
Tool=Code, Param Size=-
2025.11
60.6
Feedback
Search any
task
Search any
task