Claude Fable 5 is the best Anthropic model for coding, with a 62.0 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. Claude Opus 4.8 (56.7) and Claude Opus 4.7 (52.5) 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 Anthropic model for coding, with a 62.0 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. Claude Opus 4.8 (56.7) and Claude Opus 4.7 (52.5) round out the top three.
Claude Opus 4.8 (56.7) is the closest alternative on this metric, followed by Claude Opus 4.7 (52.5). See the full ranking above for the tradeoffs.
modelgrep tracks 16 Anthropic models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Claude Fable 5. 13 of them qualify for this ranking.