Leaderboard
AI model leaderboard
Dynamic ranking of frontier models on how well they handle real editorial tasks — chat, coding, writing, and everyday work — scored by our monthly two-way comparison rounds.
| Rank | Model | Hub Score | Test sessions | API price / 1M | Context |
|---|---|---|---|---|---|
| 1 | Midjourney v7 Midjourney · Proprietary | 1741 +12 / -12 | 2,214 | From $10/mo subscription | — |
| 2 | GPT Image 1 OpenAI · Proprietary | 1718 +13 / -13 | 1,985 | From $0.04/image via API | — |
| 3 | Imagen 4 Google · Proprietary | 1712 +14 / -14 | 1,742 | From $0.04/image via API | — |
| 4 | FLUX 1.1 Pro Black Forest Labs · Proprietary | 1697 +15 / -15 | 1,618 | From $0.04/image via API | — |
| 5 | Ideogram 3.0 Ideogram · Proprietary | 1668 +16 / -16 | 1,377 | From $0.08/image | — |
| 6 | Recraft V3 Recraft · Proprietary | 1654 +16 / -16 | 1,120 | Credits from $12/mo | — |
| 7 | Stable Diffusion 3.5 Stability AI · Open source | 1631 +17 / -17 | 1,866 | Free self-hosted · API from $0.035/image | — |
How this works: Hub Score is our editorial Elo — the same set of real tasks goes to every model each month, our editors compare outputs two at a time, and the score moves as rounds complete. The +a/-b range is the confidence interval. API prices are public list prices per 1M tokens (input/output), approximate — always confirm on the vendor's page. We run this ourselves; it is not a vendor benchmark and we are not affiliated with any lab or arena.