UI-Bench Leaderboard
Comprehensive evaluation of AI tools for frontend generation, ranked by expert assessment across diverse design challenges.
UI-Bench Leaderboard
UI-Bench Leaderboard
Overall leaderboard aggregated across n = 4,047 blinded pairwise matches
Tool win rates vs loss rates
RatingWin Rate
Orchids
Orchids
Rating (μ): 30.08
95% CI: [26.61, 33.55]
Win rate: 67.5%
30.0867.5%
Figma Make
Figma Make
Rating (μ): 27.46
95% CI: [24.11, 30.81]
Win rate: 57.1%
27.4657.1%
Lovable
Lovable
Rating (μ): 27.14
95% CI: [23.77, 30.51]
Win rate: 54.8%
27.1454.8%
Anything
Anything
Rating (μ): 25.46
95% CI: [22.15, 28.77]
Win rate: 51.2%
25.4651.2%
Bolt
Bolt
Rating (μ): 24.44
95% CI: [21.15, 27.73]
Win rate: 48.9%
24.4448.9%
Magic Patterns
Magic Patterns
Rating (μ): 24.23
95% CI: [20.90, 27.56]
Win rate: 47.0%
24.2347.0%
Same.new
Same.new
Rating (μ): 23.57
95% CI: [20.24, 26.90]
Win rate: 45.8%
23.5745.8%
Base44 by Wix
Base44 by Wix
Rating (μ): 23.47
95% CI: [20.16, 26.78]
Win rate: 47.4%
23.4747.4%
v0
v0
Rating (μ): 22.24
95% CI: [18.87, 25.61]
Win rate: 41.2%
22.2441.2%
Replit
Replit
Rating (μ): 20.95
95% CI: [17.56, 24.34]
Win rate: 38.9%
20.9538.9%
Rankings based on TrueSkill model
Bar lengths are proportional to ratings
Win Rate
Blue bars represent win rates as percentages
UI-Bench Leaderboard
Complete performance data with sortable columns
| Rank | Tool | Rating (μ) | Uncertainty (σ) | 95% CI | Win Rate |
|---|---|---|---|---|---|
| #1 | Orchids | 30.08 | 1.77 | [26.61, 33.55] | 67.5% |
| #2 | Figma Make | 27.46 | 1.71 | [24.11, 30.81] | 57.1% |
| #3 | Lovable | 27.14 | 1.72 | [23.77, 30.51] | 54.8% |
| #4 | Anything | 25.46 | 1.69 | [22.15, 28.77] | 51.2% |
| #5 | Bolt | 24.44 | 1.68 | [21.15, 27.73] | 48.9% |
| #6 | Magic Patterns | 24.23 | 1.70 | [20.90, 27.56] | 47.0% |
| #7 | Same.new | 23.57 | 1.70 | [20.24, 26.90] | 45.8% |
| #8 | Base44 by Wix | 23.47 | 1.69 | [20.16, 26.78] | 47.4% |
| #9 | v0 | 22.24 | 1.72 | [18.87, 25.61] | 41.2% |
| #10 | Replit | 20.95 | 1.73 | [17.56, 24.34] | 38.9% |