Kling Image 4.0 ranks #7 in text-to-image and #6 in image editing on Artificial Analysis
Shruti_0810 · x · 2026-11-18
Kling Image 4.0 lands #7 in text-to-image and #6 in image editing on Artificial Analysis' blind-vote Elo leaderboards, placing above Nano Banana. Screenshots show MAI-Image-2.7 (Elo 1215) and GPT Image 2.6 Sunburst/Flare (max) leading image editing, while GPT Image 2.6 Sunburst (max, Elo 1261) tops text-to-image. The author's bigger takeaway: the model's strength across both generation and editing gives a more complete picture of what an image model offers than any single ranking.
More from Multimodal
- Seedance 2.5 4K video generation goes global in CapCut PC, 90% off first month — HeyNayeem · 2026-11-19
- fal launches Idol Max and Idol Max Turbo: one image to game-ready GLB mesh with UVs and auto-rig — OdinLovis · 2026-11-19
- HiT image generator learns its own abstraction hierarchy, hits 1.48 FID on ImageNet 256 — LucaAmb · 2026-11-19
- Osmo rebrands as applied AI lab, launches Posty video agent that cuts footage in under 30 min — yawnxyz · 2026-11-19
- MOSS-Image-Base nails small real-world sign text: lost cat flyers and passive-aggressive notes — Impressive-Kick293 · 2026-11-19
- Dev ports MiniMax H3 to Swift, cuts 480p video gen to ~4 min on a 16GB M1 MacBook — Lokoto123 · 2026-11-19