Independent review by Artificial Analysis: GPT Image 2.6 Flare generation speed is roughly twice that of 2.5 Flare
Artificial Analysis has released an independent benchmark. GPT Image 2.6 Flare achieves a median generation time of approximately 30 seconds at the highest quality setting, compared to about 55 seconds for GPT Image 2.5 Flare—a speed increase nearly doubling performance. The new version also scores higher on two additional benchmarks: AA-Image-T2I v2 and AA-Image-Editing v2.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original