Arena· Updated
Arena.ai has placed Reve 2.0 in the second spot on its Text-to-Image leaderboard following a significant performance jump. The model's 125-point improvement allows it to outperform flagship image generators from Google and Microsoft in human-preference testing.
The ranking highlights a competitive shift where specialized models climb against general-purpose frontier systems. By landing at #2, Reve 2.0 placed above MAI-Image-2.5, Google's Nano Banana 2, and OpenAI's GPT-Image-1.5. Its largest sub-category gains over v1.5 are in Text Rendering, Photorealistic and Cinematic Imagery, and on the editing boards it ranks #7 in Multi-Image Edit and #9 in Single-Image Edit.
The leaderboard reflects over 5.3 million human-preference votes across 66 models, with Reve 2.0's score still marked preliminary. Its second-place finish places it ahead of established proprietary generators from Google and Microsoft, while Ideogram 4.0 Quality leads open models at #9 — underscoring rapid gains for the Reve lab in competitive text-to-image quality.
Reve 2.0 has landed #2 in the Text-to-Image Arena! Scoring 1280, this puts the latest model above Nano Banana 2, MAI-Image-2.5, and GPT-Image-1.5-High Fidelity. This is a +125pt improvement over Reve v1.5. Congratulations to the @reve team on this major milestone! https://t.co/Ck7arnEzgb
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →
