LiveBench Design Layout: leaderboard
Metric: Score. Source: livebench.ai. Saturation forecast: Around December 2027. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 86.9 | #3 |
| 2 | Claude Sonnet 5.5 | 85 | #11 |
| 3 | Claude Fable 5 | 84.7 | #15 |
| 4 | Claude Fable 5.1 | 83.4 | #8 |
| 5 | Claude Opus 5 | 83 | #12 |
| 6 | GPT-6 Luna | 82.5 | #51 |
| 7 | GPT-6 Sol | 82.2 | #16 |
| 8 | Claude Haiku 5.5 | 82.2 | #28 |
| 9 | GPT-6.1 Sol | 82.1 | #9 |
| 10 | Claude Sonnet 5 | 82 | #56 |
| 11 | GPT-6 Astra | 82 | #5 |
| 12 | GPT-5.6 Sol | 81.6 | #18 |
| 13 | Grok 4.6 | 79.8 | #27 |
| 14 | Claude Opus 4.8 | 78.8 | #36 |
| 15 | Qwen 3.8 Max | 78.6 | #32 |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=livebench-design-layout · How It Works · Data refreshed daily, snapshot 2026-10-14.