Benchmark Almanac

DesignArena Proprietary Harness Slides

Playyy 1,301 tops its leaderboard
Not in model cards

Slide-making products build a presentation from a user prompt in their own harness. Users compare the decks and vote for the better one.

DesignArena open-sourced data from more than 50,000 slide generations. One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Documents and spreadsheets
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
13
Entries on its own leaderboard, 0 models we track

Playyy tops the leaderboard with 1,301

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.

13 entries. Scroll sideways for the rest. Bars start at 1,000.

  1. 1,301 Playyy
  2. 1,292 Claude Opus 5.5 (Claude Code)
  3. 1,259 Gamma 5
  4. 1,250 Moda
  5. 1,239 Replit
  6. 1,219 Manus 1.6
  7. 1,195 Claude Opus 4.6 (PPTX)
  8. 1,180 Claude Sonnet 4.6 (PPTX)
  9. 1,157 Gamma
  10. 1,151 Ultramarine
  11. 1,077 Snapdeck
  12. 1,009 Alai
  13. 1,001 SlidesGPT

Bars start at 1,000.

  1. 1 Playyy 1,301
  2. 2 Claude Opus 5.5 (Claude Code) 1,292
  3. 3 Gamma 5 1,259
  4. 4 Moda 1,250
  5. 5 Replit 1,239
  6. 6 Manus 1.6 1,219
  7. 7 Claude Opus 4.6 (PPTX) 1,195
  8. 8 Claude Sonnet 4.6 (PPTX) 1,180
  9. 9 Gamma 1,157
  10. 10 Ultramarine 1,151
  11. 11 Snapdeck 1,077
  12. 12 Alai 1,009
  13. 13 SlidesGPT 1,001

Source: Official DesignArena Proprietary Harness Slides leaderboard

#EntryScoreSettingDateSource
1 Playyy 1,301 Official leaderboard
2 Claude Opus 5.5 (Claude Code) 1,292 Official leaderboard
3 Gamma 5 1,259 Official leaderboard
4 Moda 1,250 Official leaderboard
5 Replit 1,239 Official leaderboard
6 Manus 1.6 1,219 Official leaderboard
7 Claude Opus 4.6 (PPTX) 1,195 Official leaderboard
8 Claude Sonnet 4.6 (PPTX) 1,180 Official leaderboard
9 Gamma 1,157 Official leaderboard
10 Ultramarine 1,151 Official leaderboard
11 Snapdeck 1,077 Official leaderboard
12 Alai 1,009 Official leaderboard
13 SlidesGPT 1,001 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 Economic work

All 97 in Economic work
  • JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
  • GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate. Seed2.1 Pro 87.9%
  • GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
  • AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
  • CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
  • OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%