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 | Veo 3 Google · Proprietary | 1744 +13 / -13 | 1,836 | From $0.50/second via API | — |
| 2 | Sora 2 OpenAI · Proprietary | 1722 +14 / -14 | 1,648 | Included in ChatGPT Pro; API usage-based | — |
| 3 | Kling 2.5 Kuaishou · Proprietary | 1708 +15 / -15 | 1,523 | Credits from $10/mo | — |
| 4 | Runway Gen-4 Runway · Proprietary | 1695 +15 / -15 | 1,476 | Credits from $12/mo | — |
| 5 | Hailuo 02 MiniMax · Proprietary | 1671 +16 / -16 | 1,288 | Credits from $9.9/mo | — |
| 6 | Pika 2.2 Pika Labs · Proprietary | 1643 +16 / -16 | 1,194 | Credits from $8/mo | — |
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.