Best AI for Programming
Compare AI models for software development — code generation, debugging, code review, refactoring, and architecture design.Rankings combine multiple benchmark scores weighted by relevance to this use case. Updated August 2026.
Why This Matters
Programming is one of the most common AI workloads — and the best model depends heavily on the specific task. A model that excels at creative writing may struggle with structured data extraction, and vice versa.
We built this use-case ranking by combining multiple benchmark categories with weights tuned to match real-world usage patterns. For programming, the score emphasizes the benchmarks that matter most: task accuracy, output quality, and consistency. Speed and cost are factored in but secondary to quality.
All scores are from public independent benchmarks. For a broader view across all tasks, see the overall LLM leaderboard or the expert picks page.
Quick Answer
The best AI models for programming are:1. Claude Fable 5.1 (Anthropic, score: 94.1), 2. Claude Fable 5 (Anthropic, score: 85.6), 3. Claude Fable 5.1 (XHigh) (Anthropic, score: 85.5).
| # | Model | Provider | Score | Speed | Price (output) |
|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | Anthropic | 94.1 | 85 t/s | $15/M |
| 2 | Claude Fable 5 | Anthropic | 85.6 | 71 t/s | $50/M |
| 3 | Claude Fable 5.1 (XHigh) | Anthropic | 85.5 | 78 t/s | $15/M |
| 4 | Claude Fable 5.1 (High) | Anthropic | 85.5 | 92 t/s | $15/M |
| 5 | Claude Fable 5.1 (Medium) | Anthropic | 85.5 | 104 t/s | $15/M |
| 6 | Claude Fable 5.1 (Low) | Anthropic | 85.5 | 118 t/s | $15/M |
| 7 | Claude Opus 5.5 | Anthropic | 84.3 | 68 t/s | $25/M |
| 8 | GPT-6 Astra | OpenAI | 76.9 | 82 t/s | $50/M |
| 9 | Kimi K3 | Moonshot AI | 76.7 | 37 t/s | $15/M |
| 10 | Claude Opus 5.5 (XHigh) | Anthropic | 74.9 | 62 t/s | $25/M |
| 11 | Claude Opus 5.5 (High) | Anthropic | 74.9 | 74 t/s | $25/M |
| 12 | Claude Opus 5.5 (Medium) | Anthropic | 74.9 | 82 t/s | $25/M |
| 13 | Claude Opus 5.5 (Low) | Anthropic | 74.9 | 92 t/s | $25/M |
| 14 | GPT-6 Astra (xhigh) | OpenAI | 70.6 | 76 t/s | $50/M |
| 15 | GPT-6 Astra (high) | OpenAI | 70.6 | 90 t/s | $50/M |