Benchmark Almanac

DesignArena Builder

Replit (Design Mode) 1,268 tops its leaderboard
Not in model cards

AI app builders make full-stack web and mobile apps from the same user prompt. Users compare the results and vote for the better one.

One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Building whole projects
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
18
Entries on its own leaderboard, 0 models we track

Replit (Design Mode) tops the leaderboard with 1,268

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

18 entries. Scroll sideways for the rest. Bars start at 1,100.

  1. 1,268 Replit (Design Mode)
  2. 1,256 Emergent
  3. 1,252 Anything
  4. 1,243 Lovable
  5. 1,238 Floot
  6. 1,234 Magic Patterns
  7. 1,229 Orchids V2
  8. 1,226 Same.new
  9. 1,218 Base 44
  10. 1,211 Figma Make
  11. 1,194 Macaly
  12. 1,190 Mocha
  13. 1,190 v0
  14. 1,185 Cosmic.new
  15. 1,182 Bolt.new
  16. 1,182 Google AI Studio
  17. 1,165 Aura (Sonnet 4.5)
  18. 1,134 Canva

Bars start at 1,100.

  1. 1 Replit (Design Mode) 1,268
  2. 2 Emergent 1,256
  3. 3 Anything 1,252
  4. 4 Lovable 1,243
  5. 5 Floot 1,238
  6. 6 Magic Patterns 1,234
  7. 7 Orchids V2 1,229
  8. 8 Same.new 1,226
  9. 9 Base 44 1,218
  10. 10 Figma Make 1,211
  11. 11 Macaly app-08-19 1,194
  12. 12 Mocha 1,190
  13. 13 v0 1,190
  14. 14 Cosmic.new 1,185
  15. 15 Bolt.new 1,182
  16. 16 Google AI Studio 1,182
  17. 17 Aura (Sonnet 4.5) 1,165
  18. 18 Canva 1,134

Source: Official DesignArena Builder leaderboard

#EntryScoreSettingDateSource
1 Replit (Design Mode) 1,268 Official leaderboard
2 Emergent 1,256 Official leaderboard
3 Anything 1,252 Official leaderboard
4 Lovable 1,243 Official leaderboard
5 Floot 1,238 Official leaderboard
6 Magic Patterns 1,234 Official leaderboard
7 Orchids V2 1,229 Official leaderboard
8 Same.new 1,226 Official leaderboard
9 Base 44 1,218 Official leaderboard
10 Figma Make 1,211 Official leaderboard
11 Macaly 1,194 app-08-19 Official leaderboard
12 Mocha 1,190 Official leaderboard
13 v0 1,190 Official leaderboard
14 Cosmic.new 1,185 Official leaderboard
15 Bolt.new 1,182 Official leaderboard
16 Google AI Studio 1,182 Official leaderboard
17 Aura (Sonnet 4.5) 1,165 Official leaderboard
18 Canva 1,134 Official leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471