Image generation

Which model draws the picture. Four answers — best value for money, best there is, best with open weights, cheapest that still works.

Judged on

• Artificial Analysis · Text to Image Arena

Artificial Analysis · Text to Image Arena is kept for want of a better one: its entrants sit within a few per cent of each other, so whoever leads it leads by very little. Read the pick above as the best of a crowd rather than a clear winner.

Capability is a model's mean percentile across the boards below, on each board's widest metric. Prices are quoted as you are billed them; where a model charges separately to read and to write, the two are ranked against each other at one part in to three parts out, which for this field puts the middle at $0.05 an image. Best value for money is the most capable at or under that middle, and cheapest is the least expensive of those above the middle for capability — without that second floor the cheapest answer is reliably the worst model in the category. Figures read 2026-09-16.

All the picks