VERIFIEDNov 222026
Is Imagen 4 state of the art?#45Best current rank: #45 in Image generation, as of Nov 22, 2026.
As of Nov 22, 2026, Imagen 4 is ranked #45 in Image generation (since Nov 22, 2026; sources LMArena Text-to-Image; methodology v1.0). Ranked #45 in Image generation.
At a glance
Facts and scores
Imagen 4 is a closed-weights text model from Google DeepMind, may 20, 2025; no public parameter count and no public price.
How it scores
- On LMArena Text-to-Image it scores 1128 (CI 1125–1130), #58 of 108 (top 54%); 301 behind GPT Image 2.5 Sunburst; level with Krea 2 above and Qwen Image 2512 is 3 below.
History
First result on isitsota: Nov 20, 2026. Best overall rank so far: #45 in Image generation, first held Nov 22, 2026.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text-to-Image Imagen 4 (generate-001) | 1128 1125–1130 | 2026-11-20 | INDEP. | snap_c3a0f5dc8d98 |
Reign history
Where it sits in the succession
Crown intervals for this model are still empty.
Honest about the gaps
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| Image generation | #45 in this category | #45 | GPT Image 2.5 Sunburst |
Links
Related pages
Is Imagen 4 SOTA?
Best current rank: #45 in Image generation, as of Nov 22, 2026.
What is Imagen 4 best at?
As of Nov 22, 2026, Imagen 4 is ranked #45 in Image generation (since Nov 22, 2026; sources LMArena Text-to-Image).