findeverythingaiInteractive benchmark desk

PUBLISHED BENCHMARK RESULTS

Aider Code Editing

Historical code editing runs using Aider. Task counts and editing formats vary between runs.

These are publisher-reported model and agent runs. Agent version, reasoning effort or editing format, environment and source dates may differ. Task counts do not prove identical evaluation conditions. Compare setups before drawing conclusions.

Reported costs are evaluation totals in USD, not current API prices. Missing results are not scores of zero. No score is a universal recommendation.

Historical coverage: this source contains older Aider evaluations. Refreshing the source does not make the underlying results current.

Latest source result: 2024-12-21 · Source check: 2026-10-08 · Source checked successfully

Benchmark publisher ↗ · Apache-2.0 ↗ · Full methodology and provenance

133 tasks

93 runs · Pass rate after 2 attempts. Ranks apply within this task cohort.

  1. Filtered rank 1

    claude-3-5-sonnet-20241022

    Aider · 0.59.2.devSource run ↗
    diff · 133 tasks
    84.2%
    Compare
  2. Filtered rank 2

    o1

    Aider · 0.69.2.devSource run ↗
    diff · 133 tasks
    84.2%
    Compare
  3. Filtered rank 3

    gemini-exp-1206 (whole)

    Aider · 0.67.1.devSource run ↗
    whole · 133 tasks
    80.5%
    Compare
  4. Filtered rank 4

    o1-preview

    Aider · 0.56.1.devSource run ↗
    diff · 133 tasks
    79.7%
    Compare
  5. Filtered rank 5

    claude-3.5-sonnet-20240620

    Aider · 0.42.1-devSource run ↗
    diff · 133 tasks
    77.4%
    Compare
  6. Filtered rank 6

    claude-3-5-haiku-20241022

    Aider · 0.61.1.devSource run ↗
    diff · 133 tasks
    75.2%
    Compare
  7. Filtered rank 7

    DeepSeek Coder V2 0724

    Aider · 0.45.2-devSource run ↗
    diff · 133 tasks
    72.9%
    Compare
  8. Filtered rank 8

    gpt-4o-2024-05-13

    Aider · 0.34.1-devSource run ↗
    diff · 133 tasks
    72.9%
    Compare
  9. Filtered rank 9

    ollama/qwen2.5-coder:32b

    Aider · 0.65.2.devSource run ↗
    whole · 133 tasks
    72.9%
    Compare
  10. Filtered rank 10

    DeepSeek V2.5

    Aider · 0.55.1.devSource run ↗
    diff · 133 tasks
    72.2%
    Compare
  11. Filtered rank 11

    DeepSeek-V2.5-1210

    Aider · 0.67.1.devSource run ↗
    diff · 133 tasks
    72.2%
    Compare
  12. Filtered rank 12

    openai/chatgpt-4o-latest

    Aider · 0.58.2.devSource run ↗
    diff · 133 tasks
    72.2%
    Compare
  13. Filtered rank 13

    Qwen2.5-Coder-32B-Instruct

    Aider · 0.59.2.devSource run ↗
    diff · 133 tasks
    71.4%
    Compare
  14. Filtered rank 14

    gpt-4o-2024-08-06

    Aider · 0.48.1-devSource run ↗
    diff · 133 tasks
    71.4%
    Compare
  15. Filtered rank 15

    gpt-4o-2024-11-20

    Aider · 0.63.3.devSource run ↗
    diff · 133 tasks
    71.4%
    Compare
  16. Filtered rank 16

    o1-mini (whole)

    Aider · 0.56.1.devSource run ↗
    whole · 133 tasks
    70.7%
    Compare
  17. Filtered rank 17

    DeepSeek Chat V2 0628

    Aider · 0.45.2-devSource run ↗
    diff · 133 tasks
    69.9%
    Compare
  18. Filtered rank 18

    gemini-2.0-flash-exp

    Aider · 0.68.1.devSource run ↗
    diff · 133 tasks
    69.9%
    Compare
  19. Filtered rank 19

    Qwen2.5-Coder-14B-Instruct

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    69.2%
    Compare
  20. Filtered rank 20

    gemini-exp-1206 (diff)

    Aider · 0.67.1.devSource run ↗
    diff · 133 tasks
    69.2%
    Compare
  21. Filtered rank 21

    claude-3-opus-20240229

    Aider · 0.30.2-devSource run ↗
    diff · 133 tasks
    68.4%
    Compare
  22. Filtered rank 22

    gpt-4-0613

    Aider · 0.18.2-devSource run ↗
    diff · 133 tasks
    67.7%
    Compare
  23. Filtered rank 23

    Dracarys2-72B-Instruct

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    66.9%
    Compare
  24. Filtered rank 24

    gemini-1.5-pro-exp-0827

    Aider · 0.53.1-devSource run ↗
    diff-fenced · 133 tasks
    66.9%
    Compare
  25. Filtered rank 25

    gpt-4-0125-preview

    Aider · 0.22.1-devSource run ↗
    udiff · 133 tasks
    66.2%
    Compare
  26. Filtered rank 26

    gpt-4-0314

    Aider · 0.31.2-devSource run ↗
    diff · 133 tasks
    66.2%
    Compare
  27. Filtered rank 27

    llama-3.1-405b-instruct (whole)

    Aider · 0.45.2-devSource run ↗
    whole · 133 tasks
    66.2%
    Compare
  28. Filtered rank 28

    Mistral Large (2411)

    Aider · 0.63.3.devSource run ↗
    diff · 133 tasks
    65.4%
    Compare
  29. Filtered rank 29

    gemini-1.5-pro-002

    Aider · 0.57.2.devSource run ↗
    diff-fenced · 133 tasks
    65.4%
    Compare
  30. Filtered rank 30

    gpt-4-1106-preview

    Aider · 0.33.1-devSource run ↗
    udiff · 133 tasks
    65.4%
    Compare
  31. Filtered rank 31

    openrouter/qwen/qwen-2.5-coder-32b-instruct

    Aider · 0.63.3.devSource run ↗
    diff · 133 tasks
    65.4%
    Compare
  32. Filtered rank 32

    qwen-2.5-72b-instruct (bf16)

    Aider · 0.56.1.devSource run ↗
    diff · 133 tasks
    65.4%
    Compare
  33. Filtered rank 33

    yi-lightning

    Aider · 0.67.1.devSource run ↗
    whole · 133 tasks
    65.4%
    Compare
  34. Filtered rank 34

    gpt-4-turbo-2024-04-09 (udiff)

    Aider · 0.30.2-devSource run ↗
    udiff · 133 tasks
    63.9%
    Compare
  35. Filtered rank 35

    llama-3.1-405b-instruct (diff)

    Aider · 0.45.2-devSource run ↗
    diff · 133 tasks
    63.9%
    Compare
  36. Filtered rank 36

    nousresearch/hermes-3-llama-3.1-405b

    Aider · 0.54.8-devSource run ↗
    whole · 133 tasks
    63.9%
    Compare
  37. Filtered rank 37

    ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    63.9%
    Compare
  38. Filtered rank 38

    ollama/qwen2.5-coder:14b

    Aider · 0.65.2.devSource run ↗
    whole · 133 tasks
    61.7%
    Compare
  39. Filtered rank 39

    gemini-exp-1114

    Aider · 0.63.2.devSource run ↗
    diff · 133 tasks
    60.9%
    Compare
  40. Filtered rank 40

    Mistral Large 2 (2407)

    Aider · 0.45.2-devSource run ↗
    whole · 133 tasks
    60.2%
    Compare
  41. Filtered rank 41

    llama-3.3-70b-instruct

    Aider · 0.67.1.devSource run ↗
    diff · 133 tasks
    59.4%
    Compare
  42. Filtered rank 42

    Grok-2

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    58.6%
    Compare
  43. Filtered rank 43

    llama-3.1-70b-instruct

    Aider · 0.45.2-devSource run ↗
    whole · 133 tasks
    58.6%
    Compare
  44. Filtered rank 44

    ollama/qwen2.5:32b-instruct-q8_0

    Aider · 0.56.1.devSource run ↗
    whole · 133 tasks
    58.6%
    Compare
  45. Filtered rank 45

    Qwen2.5-Coder-7B-Instruct

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    57.9%
    Compare
  46. Filtered rank 46

    gemini-exp-1121

    Aider · 0.63.3.devSource run ↗
    diff · 133 tasks
    57.9%
    Compare
  47. Filtered rank 47

    gpt-3.5-turbo-0301

    Aider · 0.16.4-devSource run ↗
    whole · 133 tasks
    57.9%
    Compare
  48. Filtered rank 48

    gemini-1.5-pro-001

    Aider · 0.31.2-devSource run ↗
    diff-fenced · 133 tasks
    57.1%
    Compare
  49. Filtered rank 49

    Qwen2 72B Instruct

    Aider · 0.37.1-devSource run ↗
    whole · 133 tasks
    55.6%
    Compare
  50. Filtered rank 50

    gpt-4o-mini

    Aider · 0.44.1-devSource run ↗
    whole · 133 tasks
    55.6%
    Compare
  51. Filtered rank 51

    Grok-2-mini

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    54.9%
    Compare
  52. Filtered rank 52

    Llama-3.1-Nemotron-70B-Instruct-HF

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    54.9%
    Compare
  53. Filtered rank 53

    claude-3-sonnet-20240229

    Aider · 0.25.1-devSource run ↗
    whole · 133 tasks
    54.9%
    Compare
  54. Filtered rank 54

    Nova Pro

    Aider · 0.66.1.devSource run ↗
    whole · 133 tasks
    54.1%
    Compare
  55. Filtered rank 55

    Yi Coder 9B Chat

    Aider · 0.54.13.devSource run ↗
    whole · 133 tasks
    54.1%
    Compare
  56. Filtered rank 56

    ollama/qwen2.5:32b

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    54.1%
    Compare
  57. Filtered rank 57

    gemini-1.5-flash-exp-0827

    Aider · 0.53.1-devSource run ↗
    whole · 133 tasks
    52.6%
    Compare
  58. Filtered rank 58

    qwen2.5-coder:7b-instruct-q8_0

    Aider · 0.56.0Source run ↗
    whole · 133 tasks
    51.9%
    Compare
  59. Filtered rank 59

    codestral-2405

    Aider · 0.37.1-devSource run ↗
    whole · 133 tasks
    51.1%
    Compare
  60. Filtered rank 60

    gemini-1.5-flash-002 (0924)

    Aider · 0.57.2.devSource run ↗
    whole · 133 tasks
    51.1%
    Compare
  61. Filtered rank 61

    gpt-3.5-turbo-0125

    Aider · 0.33.1-devSource run ↗
    whole · 133 tasks
    50.4%
    Compare
  62. Filtered rank 62

    gpt-3.5-turbo-0613

    Aider · 0.16.4-devSource run ↗
    whole · 133 tasks
    50.4%
    Compare
  63. Filtered rank 63

    qwen2:72b-instruct-q8_0

    Aider · 0.37.1-devSource run ↗
    whole · 133 tasks
    49.6%
    Compare
  64. Filtered rank 64

    Codestral-22B-v0.1-Q4_K_M

    Aider · 0.56.1.devSource run ↗
    whole · 133 tasks
    48.1%
    Compare
  65. Filtered rank 65

    codestral:22b-v0.1-q8_0

    Aider · 0.37.1-devSource run ↗
    whole · 133 tasks
    48.1%
    Compare
  66. Filtered rank 66

    claude-3-haiku-20240307

    Aider · 0.41.1-devSource run ↗
    whole · 133 tasks
    47.4%
    Compare
  67. Filtered rank 67

    ollama/codestral

    Aider · 0.57.2.devSource run ↗
    whole · 133 tasks
    45.9%
    Compare
  68. Filtered rank 68

    yi-coder:9b-chat-q4_0

    Aider · 0.54.13.devSource run ↗
    whole · 133 tasks
    45.1%
    Compare
  69. Filtered rank 69

    WizardLM-2 8x22B

    Aider · 0.31.2-devSource run ↗
    whole · 133 tasks
    44.4%
    Compare
  70. Filtered rank 70

    gemini-1.5-flash-latest

    Aider · 0.37.1-devSource run ↗
    whole · 133 tasks
    44.4%
    Compare
  71. Filtered rank 71

    ollama/yi-coder:9b-chat-fp16

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    43.6%
    Compare
  72. Filtered rank 72

    Reflection-70B

    Aider · 0.55.1.devSource run ↗
    whole · 133 tasks
    42.1%
    Compare
  73. Filtered rank 73

    Qwen2.5-Coder-3B-Instruct

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    39.1%
    Compare
  74. Filtered rank 74

    Command R (08-24)

    Aider · 0.56.1.devSource run ↗
    whole · 133 tasks
    38.3%
    Compare
  75. Filtered rank 75

    Command R+ (08-24)

    Aider · 0.56.1.devSource run ↗
    whole · 133 tasks
    38.3%
    Compare
  76. Filtered rank 76

    gemini-1.5-flash-8b-exp-0827

    Aider · 0.53.1-devSource run ↗
    whole · 133 tasks
    38.3%
    Compare
  77. Filtered rank 77

    gemini-1.5-flash-8b-exp-0924

    Aider · 0.57.2.devSource run ↗
    whole · 133 tasks
    38.3%
    Compare
  78. Filtered rank 78

    ollama/mistral-small

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    38.3%
    Compare
  79. Filtered rank 79

    llama-3.1-8b-instruct

    Aider · 0.45.2-devSource run ↗
    whole · 133 tasks
    37.6%
    Compare
  80. Filtered rank 80

    qwen1.5-110b-chat

    Aider · 0.31.2-devSource run ↗
    whole · 133 tasks
    37.6%
    Compare
  81. Filtered rank 81

    gemma2:27b-instruct-q8_0

    Aider · 0.43.0Source run ↗
    whole · 133 tasks
    36.1%
    Compare
  82. Filtered rank 82

    codeqwen:7b-chat-v1.5-q8_0

    Aider · 0.37.1-devSource run ↗
    whole · 133 tasks
    34.6%
    Compare
  83. Filtered rank 83

    ollama/mistral-nemo:12b-instruct-2407-q4_K_M

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    33.1%
    Compare
  84. Filtered rank 84

    ollama/codegeex4

    Aider · 0.57.2.devSource run ↗
    whole · 133 tasks
    32.3%
    Compare
  85. Filtered rank 85

    Qwen2.5-Coder-1.5B-Instruct

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    31.6%
    Compare
  86. Filtered rank 86

    command-r-plus

    Aider · 0.31.2-devSource run ↗
    whole · 133 tasks
    31.6%
    Compare
  87. Filtered rank 87

    ollama/hermes3:8b-llama3.1-fp16

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    30.1%
    Compare
  88. Filtered rank 88

    ollama/wojtek/opencodeinterpreter:6.7b

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    30.1%
    Compare
  89. Filtered rank 89

    ollama/llama3.2:3b-instruct-fp16

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    26.3%
    Compare
  90. Filtered rank 90

    ollama/tulu3

    Aider · 0.65.2.devSource run ↗
    whole · 133 tasks
    26.3%
    Compare
  91. Filtered rank 91

    ollama/hermes3

    Aider · 0.58.1.devSource run ↗
    whole · 133 tasks
    22.6%
    Compare
  92. Filtered rank 92

    ollama/granite3-dense:8b

    Aider · 0.65.2.devSource run ↗
    whole · 133 tasks
    20.3%
    Compare
  93. Filtered rank 93

    Qwen2.5-Coder-0.5B-Instruct

    Aider · 0.59.2.devSource run ↗
    whole · 133 tasks
    14.3%
    Compare

132 tasks

2 runs · Pass rate after 2 attempts. Ranks apply within this task cohort.

  1. Filtered rank 1

    gpt-3.5-turbo-1106

    Aider · 0.30.2-devSource run ↗
    whole · 132 tasks
    56.1%
    Compare
  2. Filtered rank 2

    llama3-70b-8192

    Aider · 0.31.2-devSource run ↗
    diff · 132 tasks
    49.2%
    Compare

225 tasks

1 runs · Pass rate after 2 attempts. Ranks apply within this task cohort.

  1. Filtered rank 1

    o1-mini-2024-09-12

    Aider · 0.69.2.devSource run ↗
    whole · 225 tasks
    27.1%
    Compare

36 tasks

1 runs · Pass rate after 2 attempts. Ranks apply within this task cohort.

  1. Filtered rank 1

    o1-mini

    Aider · 0.56.1.devSource run ↗
    diff · 36 tasks
    61.1%
    Compare

33 tasks

1 runs · Pass rate after 2 attempts. Ranks apply within this task cohort.

  1. Filtered rank 1

    gpt-4-turbo-2024-04-09 (diff)

    Aider · 0.28.1-devSource run ↗
    diff · 33 tasks
    57.6%
    Compare