After falling behind for several months, OpenAI has made a significant comeback at the end of the year with its latest release, the GPT Image 1.5 model.
Scientists confirm: This is the most effective way to get your cat’s attention, according to new research
Elderly Couple Refuses Reserved Seats—Viral Train Standoff Sparks Fiery Debate on Courtesy
By the end of 2025, the image generation sector saw fierce competition between Google and OpenAI. Google took the lead with its release of Nano Banana Pro, which quickly captured the attention of users and topped the Text-to-Image Arena rankings in November. OpenAI countered in December with the introduction of GPT Image 1.5, seamlessly integrated into ChatGPT, which then took the lead in the rankings for that month.
The Top 10 Image Generators of December 2025
In March of the same year, OpenAI had retired its aging DALL-E model in favor of the more contemporary 4o Image Generation model, aligning more closely with the industry standards set by its competitors. However, the company then seemed to rest on its laurels, gradually losing ground in the market. The launch of Nano Banana Pro was a wake-up call for OpenAI, prompting them to step up their game. GPT Image 1.5 brought several improvements: better text rendering, more accurate face generation, and adherence to user instructions. Additionally, this new model could transform images without needing to create new ones from scratch.
Nano Banana Pro remains close behind in second place, followed by Black Forest. The German company, previously famous for its FLUX model, had not made the podium for several months but achieved it with the release of FLUX 2 at the end of November, with three variants making it into the top 10. In contrast, some companies that were popular during the boom of 2023-2024 have now plummeted to lower ranks, such as Leonardo.Ai (19th), Recraft (23rd), Ideogram (28th), Reve (29th), and Midjourney (43rd).
Why You Should Never Reheat These Foods in the Microwave – The Hidden Dangers Experts Warn About
I tried the top 5 guard dogs—here’s what makes these breeds the ultimate protectors
Here are the ten most efficient image generation models in December 2025:
- GPT Image 1.5 high (OpenAI): 1252 (Elo score)
- Nano Banana Pro – Gemini 3 (Google): 1223
- FLUX.2 [max] (Black Forest Labs): 1211
- FLUX.2 [pro] (Black Forest Labs): 1202
- Seedream 4.0 (ByteDance): 1193
- FLUX.2 [flex] (Black Forest Labs): 1186
- Seedream 4.5 (ByteDance): 1169
- Imagen 4 Ultra Preview 0606 (Google): 1164
- Nano Banana – Gemini 2.5 (Google): 1163
- ImagineArt 1.5 Preview (ImagineArt): 1159
See the complete ranking
Ranking Criteria of the Text-to-Image Arena
The Text-to-Image Arena rankings are developed by the independent entity Artificial Analysis, based on head-to-head model comparisons judged by users. In each matchup, both models are given the same prompt, and the user selects which model’s output they prefer. The results contribute to an Elo score for each model, which fluctuates based on performance: defeating a higher-ranked competitor boosts the score, while losing to a lower-ranked one causes it to drop.
Similar Posts
- AI Showdown: Top 10 Image Generators of October 2025 Unveiled!
- AI Showdown: Top 10 Image Generators of June 2025 Unveiled!
- AI Revolution: Top 10 Image Generators of August 2025 Unveiled!
- AI Image Generators: Top 10 Powerhouses of November 2025!
- AI Revolution: Top 10 Image Generators of September 2025 Unveiled!

Jordan Park writes in-depth reviews and editorial opinion pieces for Touch Reviews. With a background in UI/UX design, Jordan offers a unique perspective on device usability and user experience across smartphones, tablets, and mobile software.