Qwen-Image-3.0-Pro Ranks #5 on Text-to-Image Arena with Major Gains
arena · x · 2026-08-05
According to the latest Text-to-Image Arena leaderboard, Alibaba's Qwen-Image-3.0-Pro has secured the #5 spot overall with a score of 1263, showing a significant leap from the previous 2.0 version (ranked #15, 1191 pts).
The model demonstrated substantial improvements across various categories:
- Cartoon: Jumped from #16 to #4
- Commercial Design: Climbed from #16 to #6
- Text Rendering: Moved from #17 to #6
- Art: Advanced from #20 to #8
Related event: OpenAI Tops Text-to-Image Arena, Alibaba's Qwen-Image-3.0 Ranks 5th(2 posts)→
More from Models
- Mistral releases Shieldstral: 3B multimodal safety classifier runs on a single GPU — MistralAI · 2026-08-05
- Developer Marvels at DeepSeek's Pricing: Indefinite Use for Almost Zero Cost — yacineMTB · 2026-08-05
- Best On-Device AI Models for 8GB RAM Phones Updated — Jasonio · 2026-08-05
- OpenAI's Astra Model Solves 10 Open Math Problems, Disproving Connes' Rigidity Conjecture — GaryMarcus · 2026-08-05
- Pokee Launches 28B Agentic Model with 10M Token Context, Runs on a Single RTX 4090 — Scobleizer · 2026-08-05
- Qwen3.8-Max Matches GPT-5.6 in Coding Quality at a Quarter of the Cost — usamawahabkhan · 2026-08-05