modelgrep

Best OpenAI Models for Coding

Quick answer · Updated June 2026

GPT-5.4 is the best OpenAI model for coding, with a 57.2 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.5 (56.2) and GPT-5.3-Codex (53.1) round out the top three.

57.2Coding
56.8Intelligence
62 t/sSpeed
$2.50Input /M
1.1MContext

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 LLMs for code generation, debugging and agentic development.

  1. 1O
    gpt-5.4
    ReasoningToolsJSON+156.8 intel · $2.50/M · 62 t/s
    57.2
    Coding
  2. 2O
    gpt-5.5
    ReasoningToolsJSON+156.7 intel · $5.00/M · 36 t/s
    56.2
    Coding
  3. 3O
    gpt-5.3-codex
    ReasoningToolsJSON+153.6 intel · $1.75/M · 53 t/s
    53.1
    Coding
  4. 4O
    gpt-5.1
    ReasoningToolsJSON+147.7 intel · $1.25/M · 67 t/s
    44.7
    Coding
  5. 5O
    gpt-5.4-nano
    ReasoningToolsJSON+144.0 intel · $0.200/M · 60 t/s
    43.9
    Coding
  6. 6O
    gpt-5.2-codex
    ReasoningToolsJSON+149.0 intel · $1.75/M · 63 t/s
    43.0
    Coding
  7. 7O
    gpt-5-codex
    ReasoningToolsJSON+144.6 intel · $1.25/M · 43 t/s
    38.9
    Coding
  8. 8O
    gpt-5
    ReasoningToolsJSON+142.0 intel · $1.25/M · 53 t/s
    38.9
    Coding
  9. 9O
    o3
    ReasoningToolsJSON+138.4 intel · $2.00/M · 200K ctx
    38.4
    Coding
  10. 10O
    gpt-5.1-codex
    ReasoningToolsJSON+143.1 intel · $1.25/M · 79 t/s
    36.6
    Coding
  11. 11O
    gpt-5.1-codex-mini
    ReasoningToolsJSON+138.6 intel · $0.250/M · 127 t/s
    36.4
    Coding
  12. 12O
    gpt-5-mini
    ReasoningToolsJSON+141.2 intel · $0.250/M · 70 t/s
    35.3
    Coding
  13. 13O
    gpt-5.2
    ReasoningToolsJSON+133.6 intel · $1.75/M · 48 t/s
    34.7
    Coding
  14. 14O
    o1
    ReasoningToolsJSON+1$15.00/M · 15 t/s · 285ms ttft
    34.0
    Coding
  15. 15O
    gpt-oss-120b:free
    ReasoningTools33.3 intel · Free/M · 547 t/s
    28.6
    Coding
  16. 16O
    gpt-oss-120b
    ReasoningToolsJSON33.3 intel · $0.039/M · 547 t/s
    28.6
    Coding
  17. 17O
    o4-mini
    ReasoningToolsJSON+133.1 intel · $1.10/M · 122 t/s
    25.6
    Coding
  18. 18O
    gpt-5.4-mini
    ReasoningToolsJSON+123.3 intel · $0.750/M · 83 t/s
    25.3
    Coding
  19. 19O
    gpt-4o-2024-05-13
    ToolsJSONVision$5.00/M · 33 t/s · 431ms ttft
    24.2
    Coding
  20. 20O
    gpt-5-nano
    ReasoningToolsJSON+125.9 intel · $0.050/M · 400K ctx
    22.9
    Coding
  21. 21O
    gpt-4.1
    ToolsJSONVision26.3 intel · $2.00/M · 54 t/s
    21.8
    Coding
  22. 22O
    gpt-4-turbo
    ToolsJSONVision$10.00/M · 19 t/s · 1.1s ttft
    21.5
    Coding
  23. 23O
    gpt-5-chat
    JSONVision$1.25/M · 128K ctx
    21.2
    Coding
  24. 24O
    gpt-oss-20b:free
    ReasoningToolsJSON24.5 intel · Free/M · 391 t/s
    18.5
    Coding
  25. 25O
    gpt-oss-20b
    ReasoningToolsJSON24.5 intel · $0.029/M · 391 t/s
    18.5
    Coding

Frequently asked

What is the best OpenAI model for coding?

GPT-5.4 is the best OpenAI model for coding, with a 57.2 Artificial Analysis Coding Index across benchmarks like SWE-bench and SciCode. GPT-5.5 (56.2) and GPT-5.3-Codex (53.1) round out the top three.

What's a good alternative to GPT-5.4?

GPT-5.5 (56.2) is the closest alternative on this metric, followed by GPT-5.3-Codex (53.1). See the full ranking above for the tradeoffs.

How many OpenAI models are there?

modelgrep tracks 62 OpenAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by GPT-5.4. 25 of them qualify for this ranking.

More OpenAI rankings

All rankings