Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial Reasoning on ReasonMap
Loading...
55.1
Accuracy
Gemini-2.5-Pro
-0.644
13.828
28.3
42.772
Jun 11, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini-2.5-Pro
Model Type=Commercial
2026.06
55.1
GPT-5
Model Type=Commercial
2026.06
53.8
w/o SFT
Model Type=Ablation
2026.06
45.1
Gemini-2.5-Flash
Model Type=Commercial
2026.06
43.2
Qwen3-235B
Model Type=Open-Source
2026.06
30.7
PERIA-8B
Model Type=Proposed
2026.06
27.1
w/o RL
Model Type=Ablation
2026.06
21.1
Qwen3-32B
Model Type=Open-Source
2026.06
20.6
Qwen3-30B
Model Type=Open-Source
2026.06
18.2
w/o Tool
Model Type=Ablation
2026.06
13.7
Qwen3-8B
Model Type=Backbone Ba...
2026.06
12.3
R1-OneVision-7B
Model Type=Tool-Augmented
2026.06
8.2
InternVL3.5-8B
Model Type=Open-Source
2026.06
5.8
InternVL3.5-14B
Model Type=Open-Source
2026.06
4.4
Mini-o3
Model Type=Tool-Augmented
2026.06
1.6
VTool-R1-7B
Model Type=Tool-Augmented
2026.06
1.5
Feedback
Search any
task
Search any
task