NVIDIA Cosmos3-Super Models Hit Leaderboard: Text-to-Image Elo 1219, Pricing Coming Soon
ArtificialAnlys · x · 2026-07-31
Artificial Analysis updated its Text-to-Image and Image-to-Video leaderboards, adding NVIDIA's Cosmos3-Super-4Step models. On the text-to-image leaderboard, Cosmos3-Super-Text2Image (agentic) ranks 9-10 with an Elo of 1219, with pricing coming soon. The image-to-video model Cosmos3-Super-Image2Video-4Step joins the Video Arena. Top spots include OpenAI GPT Image 2 (Elo 1340), Reve 2.1 (Elo 1299), and Microsoft MAI-Image-2.5 (Elo 1270).
More from Multimodal
- Tessellation-free geometric queries on displaced surfaces cut caustics variance 10x — ssh4net · 2026-10-16
- Complex multi-link CAD mechanism finally animates, dev celebrates the breakthrough — zetalyrae · 2026-10-16
- OpenMOSS releases MOSS-Image-SFT: Apache 2.0 text-to-image model on Hugging Face — bdsqlsz · 2026-10-16
- Hyperflow open-sourced: 49 sampling steps down to 8, ~3x faster video generation — mhdfaran · 2026-10-16
- Cinematic 3D fantasy character prompt template with salvaged-robot armor — azed_ai · 2026-10-16
- Midjourney vintage woodcut style: --sref 2446102396 beaver with a cleaver — michaelrabone · 2026-10-16