AI model picker
Pick where you'll use the model (Cursor, OpenAI, Claude…), then the job — Plan, Build, Research, Chat, or Create. Rankings use different Artificial Analysis scores per job; no single model wins everything.
Ranked by multi-step work + reasoning scores (not writing-code alone)
Cursor is subscription-based (~$20–$200/mo + add-ons), not published $/1M — we show context window, plus estimated API rates only to compare relative expense
- Architect / Plan
- Execution
- Research
- General use
- Image & video
Key · Fit
Fit (0–100) is how strong a model is at “Architect / Plan” compared with the other models on this platform and budget. It uses different Artificial Analysis scores per task—so the best planner is not automatically the best builder or the cheapest chat model.
Recommended for Architect / Plan
Claude Fable 5.1
Fit 98/100 · 1M context · AA 53.4/81.6/57.9 · Est. API $10.00/$50.00 per 1M
- Most capableClaude Fable 5.1fit 98 · 1M context · $10.00/$50.00
- Highly capableClaude Opus 5fit 95 · 1M context · $5.00/$25.00
- Strong pickClaude Fable 5fit 91 · 1M context · $10.00/$50.00
- BalancedGPT-5.6 Solfit 84 · 1.1M context · $4.00/$20.00
- Good valueKimi K3fit 81 · 1.0M context · $0.239/$11.94
- Best valueGrok 4.6fit 88 · 500K context · $2.00/$6.00
Showing 31 of 56 scored models · Cursor · updated Oct 20, 2026, 2:34 PM ·