Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tactile-Semantic Reasoning on TacQuad
Loading...
5.02
LLM Judge Score
Splash-1B
3.2208
3.6879
4.155
4.6221
Jul 1, 2026
LLM Judge Score
Updated 23d ago
Evaluation Results
Method
Method
Links
LLM Judge Score
Splash-1B
Backbone=InternVL2.5-1B
2026.07
5.02
Splash-3B
Backbone=Qwen2.5-VL-3B
2026.07
4.86
TVL
Backbone=Qwen2.5-VL-3B
2026.07
4.22
TVL-(IA)3
Backbone=Qwen2.5-VL-3B
2026.07
3.84
Zero-shot
Backbone=Qwen2.5-VL-3B
2026.07
3.57
Zero-shot
Backbone=InternVL2.5-1B
2026.07
3.45
UniTouch
Backbone=LLaMA1-7B
2026.07
3.44
TVL
Backbone=LLaMA2-7B
2026.07
3.29
Feedback
Search any
task
Search any
task
