Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spatial decision-making on MiniBehavior size 12
Loading...
91.27
Success Rate
SpecFlow
44.4804
56.6277
68.775
80.9223
Jun 1, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
SpecFlow
Setting=Flow(image) +...
2026.06
91.27
Gemini-3-Flash
Setting=Naive
2026.06
90.36
DiffThinker
Setting=Flow(image) Only
2026.06
88.31
GPT-5.1
Setting=Naive
2026.06
87.45
MVoT
Setting=Autoregressive
2026.06
86.78
Qwen3-VL-32B
Setting=SFT
2026.06
72.16
Qwen3-VL-32B
Setting=GRPO
2026.06
69.04
Qwen3-VL-8B
Setting=SFT
2026.06
63.18
Qwen3-VL-8B
Setting=GRPO
2026.06
59.41
Qwen3-VL-32B
Setting=Naive
2026.06
56.71
Qwen3-VL-8B
Setting=Naive
2026.06
46.28
Feedback
Search any
task
Search any
task