List your company

2D Spatial Reasoning on GQA

65.2AccuracyGemini-2.5-Flash
38.88845.71952.5559.381Dec 9, 2025

Evaluation results

MethodLinks
Gemini-2.5-FlashModel Category=Proprietary, Tool Use=true2025.1265.2
o4-miniModel Category=Proprietary, Tool Use=true2025.1265
VALORModel Category=Open-Source, Tool Use=true2025.1264.4
Claude-3.5-HaikuModel Category=Proprietary, Tool Use=true2025.1261.3
GPT-4oModel Category=Proprietary, Tool Use=true2025.1258
VALOR-RLModel Category=Open-Source, Tool Use=true2025.1257.6
Qwen3-8BModel Category=Open-Source, Tool Use=true2025.1257.4
Gemini-2.0-FlashModel Category=Proprietary, Tool Use=true2025.1252.1
Gemma-3-12BModel Category=Open-Source, Tool Use=true2025.1246
Llama-3.2-11BModel Category=Open-Source, Tool Use=true2025.1239.9