List your company

Pairwise Scene Generation Evaluation on Procthor-10K (Easy)

75.6Score (SceneCritic) Method Aheuristic vs holodeck
52.7258.6664.670.54Apr 14, 2026

Evaluation results

MethodLinks
heuristic vs holodeckMethod A=heuristic, Method B=holodeck2026.0475.66071.32556.243.7752568.831.262.57568.8-0.0980.126-0.134——————
heuristic vs layoutgptMethod A=heuristic, Method B=layoutgpt2026.0475.66053.610093.86.287.512.5100093.887.51000.7390.491——————
heuristic vs layoutvlmMethod A=heuristic, Method B=layoutvlm2026.0475.66081.960752587.512.568.831.27587.568.80.1640.49-0.134——————
holodeck vs layoutgptMethod A=holodeck, Method B=layoutgpt2026.0471.32553.610087.512.593.86.293.86.287.593.893.80.5120.7270.691——————
holodeck vs layoutvlmMethod A=holodeck, Method B=layoutvlm2026.0471.32581.96037.562.537.562.587.512.562.562.587.5-0.045-0.0930.423——————
layoutgpt vs layoutvlmMethod A=layoutgpt, Method B=layoutvlm2026.0453.610081.96012.587.56.293.812.587.587.593.887.50.5120.7270.423——————