Supabase coding
Supabase Evalsno skills
The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better.
Rankings
Higher is betterSupabase Evals — frequently asked questions
- What is Supabase Evals?
- The same Supabase scenarios, but with none of Supabase's skills loaded — so it measures what the model already knows about building on Supabase, rather than how well it follows Supabase's supplied instructions. Higher is better.
- Which AI model scores highest on Supabase Evals?
- Kimi K3 by Moonshot AI holds the best Supabase Evals (no skills) result among tracked models, at 100% (released Jul 16 2026). Higher scores are better on this benchmark.
- What are the top 5 models on Supabase Evals?
- 1. Kimi K3 (Moonshot AI) — 100%; 2. GPT-5.6 Sol (OpenAI) — 94.7%; 2. Claude Opus 5 (Anthropic) — 94.7%; 4. Claude Sonnet 5 (Anthropic) — 78.9%; 5. GPT-5.4 mini (OpenAI) — 73.7%.
- How many models have a published Supabase Evals score?
- 5 tracked models have a published Supabase Evals (no skills) score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.