List your company

2D Spatial Reasoning on VSR

75.6AccuracyVALOR
50.53657.04363.5570.057Dec 9, 2025

Evaluation results

MethodLinks
VALORModel Category=Open-Source, Tool Use=true2025.1275.6
VALOR-RLModel Category=Open-Source, Tool Use=true2025.1270.3
o4-miniModel Category=Proprietary, Tool Use=true2025.1268.5
Gemini-2.5-FlashModel Category=Proprietary, Tool Use=true2025.1268.5
Qwen3-8BModel Category=Open-Source, Tool Use=true2025.1268.2
GPT-4oModel Category=Proprietary, Tool Use=true2025.1267.4
Gemini-2.0-FlashModel Category=Proprietary, Tool Use=true2025.1258.5
Llama-3.2-11BModel Category=Open-Source, Tool Use=true2025.1258.5
Gemma-3-12BModel Category=Open-Source, Tool Use=true2025.1257.9
Claude-3.5-HaikuModel Category=Proprietary, Tool Use=true2025.1251.5