List your company

Grounded Task Planning on GroundedPlanBench Explicit Instructions, Long Horizon

42.7TSRGemini-3-Flash
-1.7089.82121.3532.879Mar 13, 2026

Evaluation results

MethodLinks
Gemini-3-FlashVLM Category=Proprietary VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.0342.775.1
Qwen3-VL-32B + V2GPVLM Category=Open-Source VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.0325.960.3
Qwen3-VL-4B + V2GPVLM Category=Open-Source VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.0321.753.5
Qwen3-VL-32BVLM Category=Open-Source VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.031454.2
GPT 5.2 + ER1VLM Category=Proprietary VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.038.446.7
Qwen3-VL-32B + ER1VLM Category=Open-Source VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.038.445.4
Gemini-2.5-FlashVLM Category=Proprietary VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.035.629
Qwen3-VL-4BVLM Category=Open-Source VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.035.636.7
GPT 5.2 + SAM3 + ER1VLM Category=Proprietary VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.034.936.9
Qwen3-VL-32B + SAM3 + ER1VLM Category=Open-Source VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.034.942.4
Qwen3-VL-4B + ER1VLM Category=Open-Source VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.032.832.5
Qwen3-VL-4B + SAM3 + ER1VLM Category=Open-Source VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.032.830.6
GPT 5.2VLM Category=Proprietary VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.0303.7
Qwen3-VL-4B + SoMVLM Category=Open-Source VLMs, Planning Approach=Decoupled Task Planning + Spatial Grounding2026.03014.6
InternVL3.5-8BVLM Category=Open-Source VLMs, Planning Approach=End-to-End Spatially Grounded Planning2026.0300.6