This mysterious AI image generator tops the benchmark leaderboards

A mysterious artificial intelligence (AI) model is currently at the top of a benchmarking platform’s leaderboard, but no one can find any information about it. The mysterious model in question is called Red Panda and tops the rankings of the Artificial Analysis benchmark for text to image generation. The AI ​​model has surpassed major AI image generating platforms such as Replicate, Midjourney and Stability.ai. Notably, the ranking on the benchmarking platform is determined based on crowdsourced input, which raises questions about the mystery of Red Panda.

Mysterious AI model tops the benchmark leaderboard

The mention of the Red Panda AI model was first noticed in an X (formerly known as Twitter) afterhighlighting that the mysterious AI model was featured in the first position of the text-to-image leaderboard.

Artificial analysis uses the Elo ranking system, which is also used to rank chess players based on their skill level. The process is simple and the platform lets the users decide which models deserve to be ranked higher compared to the others. It randomly selects two models and adds a unique prompt. Based on the generated image, the benchmarking website then lets users choose which image better represents the prompt.

The method then continues with random models continuously pitted against each other until sufficient sample sizes are collected to rank the AI ​​models. Typically, this is a robust method of ranking AI models as a large portion of the users on the platform are AI enthusiasts and they understand the nuances of what makes an image generator good.

However, the fact that the Red Panda is in the first rank raises several questions about the ranking system. This is because there is no information about the developers or company behind the AI ​​model, no details about its architecture or fundamental model, or whether it will be launched soon.

Red Panda has an Elo score of 1,181 and an average generation time of seven seconds on the leaderboard. It outperforms AI models such as Replicate, Ideogram, Midjourney, Stability.ai, Playground AI, DALLE 3 and Amazon Bedrock.