Other people's tests — compiled and linked. Not BuildOff scores.
As stated: Ranked by strength: 1 Replit Agent 3; 2 v0 by Vercel; 3 Lindy; 4 NxCode; 5 Taskade Genesis; 6 OpenAI Agent Builder; 7 Bolt.new; 8 Same.new; 9 Emergent AI; 10 Grok Build Mode; 11 Framer AI Agents; 12 Google Stitch; 13 Antigravity; 14 Sticklight. Quick takes: backend-heavy → Replit…
COI: Author bio: 'AI Educator… DM Open for collaboration'. Not a controlled same-prompt test.
As stated: NO DECLARED RANKING in the opened post text or readable image content. Author asks 'Which one wins?'. Follow-up search from:TheoReednp for a winner post returned 0 results.
COI: Independent tester bio; no vendor link stated.
As stated: TL;DR as written: 'Replit was the most feature rich, well thought out, and powerful'; 'v0 was the best if you’re already a developer and want a technical interface'; 'Lovable and Bolt were pretty much objectively worse than the other two.' Final pick: 'If I were starting a new pr…
COI: None stated for any vendor.
As stated: NO DECLARED RANKING in the opened post text or readable image content. Author asks the audience which wins. Follow-up search from:Promptleague13 for a winner post returned 0 results.
COI: Independent tester bio; no vendor link stated.
As stated: Scores: Lovable 88 (14m, ~$8, Pass); Bolt.new 82 (18m, ~$12, Pass); Replit Agent 74 (25m, ~$5.50, Pass); v0 65 (35m, $0, Fail). Winner: Lovable.
As stated: Final scores (highest → lowest): Converge — 13/13; Replit — 5/13; v0 — 3/13; Bolt — 2/13; Lovable — 0/13.
COI: Strong — Converge is the author's product and finished 13/13 while competitors scored ≤5. Treat as vendor-adjacent.
As stated: Pairwise win rates (Table 2): Firebase highest on all four metrics (Ease 42.5%, Trust 41.2%, Visual Appeal 45.5%, Visual Appropriateness 45.1%); Bolt second; Replit third. Authors' hierarchy: 'Firebase > Bolt > Replit'. Composite scores stated: Firebase 1.933, Bolt 1.561, Replit …
COI: Study funded by Quome Inc. (acknowledgements). Quome Cloud used for deployment.
As stated: No numeric leaderboard table was readable in the fetched HTML (Table 1.1 / charts are images). Qualitative claims on the page: 'Lovable stands out for its reliability, functional consistency, and polished design'; 'v0 maintains the highest functional testing and navigation scores…
COI: Independent research firm; no vendor sponsorship stated on the opened page.
As stated: NOT VERIFIED. Search snippets suggest no single clear winner and situational guidance; do not treat as scored.
COI: Unknown.