2D Spatial Reasoning on GQA
65.2AccuracyGemini-2.5-Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.5-FlashModel Category=Proprietary, Tool Use=true2025.12 | 65.2 | |
| o4-miniModel Category=Proprietary, Tool Use=true2025.12 | 65 | |
| VALORModel Category=Open-Source, Tool Use=true2025.12 | 64.4 | |
| Claude-3.5-HaikuModel Category=Proprietary, Tool Use=true2025.12 | 61.3 | |
| GPT-4oModel Category=Proprietary, Tool Use=true2025.12 | 58 | |
| VALOR-RLModel Category=Open-Source, Tool Use=true2025.12 | 57.6 | |
| Qwen3-8BModel Category=Open-Source, Tool Use=true2025.12 | 57.4 | |
| Gemini-2.0-FlashModel Category=Proprietary, Tool Use=true2025.12 | 52.1 | |
| Gemma-3-12BModel Category=Open-Source, Tool Use=true2025.12 | 46 | |
| Llama-3.2-11BModel Category=Open-Source, Tool Use=true2025.12 | 39.9 |