Supabase Evals (Skills): leaderboard
Supabase Evals with the Supabase skills pack loaded: AI coding agents bootstrap and build real Supabase apps over 19 CLI tasks (migrations, RLS, auth, data APIs); percent of tasks with every check passed. Each model runs under its vendor-native harness (claude-code / codex / opencode).
Metric: Tasks Passed (%). Source: supabase.com. Saturation forecast: Around February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Medium) | 92.8 | #3 (Claude Opus 5.5) |
| 2 | Kimi K3 | 85.5 | #35 |
| 3 | Claude Sonnet 5.5 (Medium) | 85.5 | #14 (Claude Sonnet 5.5) |
| 4 | Grok 4.7 (High) | 82.6 | #26 (Grok 4.7) |
| 5 | GPT-6.1 Sol (Medium) | 81.2 | #7 (GPT-6.1 Sol) |
| 6 | GPT-6 Luna (Medium) | 76.8 | #61 (GPT-6 Luna) |
No result here: #6 GPT-6 Astra, #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=supabase-evals-skills · How It Works · Data refreshed daily, snapshot 2026-11-05.