Artificial Analysis says GPT Image 2.5 Flare leads 5 of its 9 text-to-image capabilities

Artificial Analysis said on September 11 that GPT Image 2.5 Flare’s largest capability leads were in Knowledge, Material and Physics—covering real-world facts, surface properties and physical behavior. It also reported narrow leads in Complex Compositions and Text Rendering. Its text-to-image arena measures nine capabilities and ten use cases. Across that full set, the evaluator said OpenAI’s image models collectively led every capability and use case it measures.