Claude Fable 5 is the best LLM for coding, with a 76.5 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.5 (74.9) and Claude Opus 4.8 (74.3) round out the top three.
AI models ranked by the Artificial Analysis Coding Index, measuring real-world software engineering ability across benchmarks like SWE-bench, SciCode and terminal tasks. The best LLMs for code generation, debugging and agentic development.
Claude Fable 5 is the best LLM for coding, with a 76.5 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.5 (74.9) and Claude Opus 4.8 (74.3) round out the top three.
GPT-5.5 (74.9) is the closest alternative on this metric, followed by Claude Opus 4.8 (74.3). See the full ranking above for the tradeoffs.