modelgrep

Best LLMs for Coding

Match · Updated July 2026

Claude Opus 5 is the best LLM for coding, with a 78.0 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.6 Sol (77.4) and GPT-5.6 Terra (76.7) round out the top three.

78.0Coding
60.7Intelligence
$5.00Input /M
1MContext

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 AI coding models for code generation, debugging and agentic development.

  1. 1anthropic logo
    claude-opus-5
    ReasoningToolsJSON+160.7 intel · $5.00/M · 1M ctx
    78.0
    Coding
  2. 2openai logo
    gpt-5.6-sol
    ReasoningToolsJSON+158.9 intel · $5.00/M · 1.1M ctx
    77.4
    Coding
  3. 3openai logo
    gpt-5.6-terra
    ReasoningToolsJSON+155.0 intel · $1.00/M · 1.1M ctx
    76.7
    Coding
  4. 4anthropic logo
    claude-fable-5
    ReasoningToolsJSON+159.9 intel · $10.00/M · 1M ctx
    76.5
    Coding
  5. 5anthropic logo
    claude-fable-5:batch
    ReasoningToolsJSON+159.9 intel · $5.00/M · 1M ctx
    76.5
    Coding
  6. 6moonshotai logo
    kimi-k3
    ReasoningToolsJSON+157.1 intel · $3.00/M · 1.0M ctx
    76.2
    Coding
  7. 7openai logo
    gpt-5.5
    ReasoningToolsJSON+154.8 intel · $5.00/M · 1.1M ctx
    74.9
    Coding
  8. 8openai logo
    gpt-5.5:batch
    ReasoningToolsJSON+154.8 intel · $2.50/M · 1.1M ctx
    74.9
    Coding
  9. 9anthropic logo
    claude-opus-4.8
    ReasoningToolsJSON+155.7 intel · $5.00/M · 1M ctx
    74.3
    Coding
  10. 10anthropic logo
    claude-opus-4.8:batch
    ReasoningToolsJSON+155.7 intel · $2.50/M · 1M ctx
    74.3
    Coding
  11. 11anthropic logo
    claude-opus-4.7
    ReasoningToolsJSON+153.5 intel · $5.00/M · 1M ctx
    73.6
    Coding
  12. 12anthropic logo
    claude-opus-4.7:batch
    ReasoningToolsJSON+153.5 intel · $2.50/M · 1M ctx
    73.6
    Coding
  13. 13x-ai logo
    grok-4.5
    ReasoningToolsJSON+153.8 intel · $2.00/M · 500K ctx
    72.4
    Coding
  14. 14anthropic logo
    claude-sonnet-5
    ReasoningToolsJSON+153.4 intel · $2.00/M · 1M ctx
    71.5
    Coding
  15. 15anthropic logo
    claude-sonnet-5:batch
    ReasoningToolsJSON+153.4 intel · $1.00/M · 1M ctx
    71.5
    Coding
  16. 16openai logo
    gpt-5.6-luna
    ReasoningToolsJSON+151.2 intel · $0.100/M · 1.1M ctx
    71.4
    Coding
  17. 17M
    muse-spark-1.1
    ReasoningToolsJSON+250.6 intel · $1.25/M · 1.0M ctx
    71.3
    Coding
  18. 18openai logo
    gpt-5.4
    ReasoningToolsJSON+151.4 intel · $2.50/M · 1.1M ctx
    71.1
    Coding
  19. 19openai logo
    gpt-5.4:batch
    ReasoningToolsJSON+151.4 intel · $1.25/M · 1.1M ctx
    71.1
    Coding
  20. 20google logo
    gemini-3.5-flash
    ReasoningToolsJSON+250.2 intel · $1.50/M · 1.0M ctx
    70.1
    Coding
  21. 21google logo
    gemini-3.5-flash:batch
    ReasoningToolsJSON+250.2 intel · $0.750/M · 1.0M ctx
    70.1
    Coding
  22. 22google logo
    gemini-3.6-flash
    ReasoningToolsJSON+250.1 intel · $1.50/M · 1.0M ctx
    69.2
    Coding
  23. 23google logo
    gemini-3.6-flash:batch
    ReasoningToolsJSON+250.1 intel · $0.750/M · 1.0M ctx
    69.2
    Coding
  24. 24z-ai logo
    glm-5.2
    ReasoningToolsJSON51.1 intel · $0.966/M · 1.0M ctx
    68.8
    Coding
  25. 25google logo
    gemini-3.1-pro-preview
    ReasoningToolsJSON+246.5 intel · $2.00/M · 1.0M ctx
    68.8
    Coding

Frequently asked

What is the best LLM for coding?

Claude Opus 5 is the best LLM for coding, with a 78.0 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.6 Sol (77.4) and GPT-5.6 Terra (76.7) round out the top three.

Which AI is best for coding?

Claude Opus 5 is the best AI model for coding, with a 78.0 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.6 Sol (77.4) and GPT-5.6 Terra (76.7) round out the top three.

What's a good alternative to Claude Opus 5?

GPT-5.6 Sol (77.4) is the closest alternative on this metric, followed by GPT-5.6 Terra (76.7). See the full ranking above for the tradeoffs.

By maker

All rankings