Sandbox Charts

Discover tools and use the data to compare them.

Dated, sourced editions

Update overdue. The latest published edition remains available.

MODELS TOP 20

Compare models by the capability you need.

Understand this edition's data

Available sources vary between models in this edition. A score does not guarantee two independent evaluations or a measure of value for money.

Latest included observation
Frozen calculation
Publication

Calculation version : models-cross-source-v1

20 entries shown in MODELS TOP 20.

  1. 01-

    gemini-4-argon-high

    gemini-4-argon-high

    100,0/100SANDBOX SCORE
    -

    Introduction

    Models

    gemini-4-argon-high

    Data

    SANDBOX score: 100,0 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#1

    1 editions in the Top 20 · best rank #1

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 677,8
    Arena WebDev ↗
    Elo Arena (texte)
    1 525,4
    Arena ↗

    Score components

    Value
    100,0/100
    Coding
    90,9/100
    Available model measurements
    100,0/100
  2. 02-

    claude-opus-5.5-high

    claude-opus-5.5-high

    99,0/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-5.5-high

    Data

    SANDBOX score: 99,0 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#2

    1 editions in the Top 20 · best rank #2

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (vision)
    1 292,7
    Arena Vision ↗
    Elo Arena (texte)
    1 507,1
    Arena ↗

    Score components

    Value
    99,0/100
    Available model measurements
    99,0/100
    Vision
    84,8/100
  3. 03-

    claude-opus-4-6-high

    claude-opus-4-6-high

    98,0/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-4-6-high

    Data

    SANDBOX score: 98,0 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#3

    1 editions in the Top 20 · best rank #3

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 546,5
    Arena WebDev ↗
    Elo Arena (vision)
    1 299,2
    Arena Vision ↗
    Elo Arena (texte)
    1 504,4
    Arena ↗

    Score components

    Value
    98,0/100
    Coding
    56,1/100
    Available model measurements
    98,0/100
    Vision
    97,0/100
  4. 04-

    claude-fable-5-high

    claude-fable-5-high

    97,0/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-fable-5-high

    Data

    SANDBOX score: 97,0 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#4

    1 editions in the Top 20 · best rank #4

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 624,7
    Arena WebDev ↗
    Elo Arena (vision)
    1 308,0
    Arena Vision ↗
    Elo Arena (texte)
    1 503,7
    Arena ↗

    Score components

    Value
    97,0/100
    Coding
    78,8/100
    Available model measurements
    97,0/100
    Vision
    100,0/100
  5. 05-

    claude-opus-4-7-high

    claude-opus-4-7-high

    96,0/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-4-7-high

    Data

    SANDBOX score: 96,0 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#5

    1 editions in the Top 20 · best rank #5

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 557,5
    Arena WebDev ↗
    Elo Arena (vision)
    1 297,8
    Arena Vision ↗
    Elo Arena (texte)
    1 501,0
    Arena ↗

    Score components

    Value
    96,0/100
    Coding
    62,1/100
    Available model measurements
    96,0/100
    Vision
    93,9/100
  6. 06-

    claude-fable-5.1-max

    claude-fable-5.1-max

    95,0/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-fable-5.1-max

    Data

    SANDBOX score: 95,0 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#6

    1 editions in the Top 20 · best rank #6

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 743,7
    Arena WebDev ↗
    Elo Arena (vision)
    1 286,4
    Arena Vision ↗
    Elo Arena (texte)
    1 500,7
    Arena ↗

    Score components

    Value
    95,0/100
    Coding
    95,5/100
    Available model measurements
    95,0/100
    Vision
    75,8/100
  7. 07-

    claude-opus-4-6

    claude-opus-4-6

    93,9/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-4-6

    Data

    SANDBOX score: 93,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#7

    1 editions in the Top 20 · best rank #7

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 537,2
    Arena WebDev ↗
    Elo Arena (vision)
    1 294,5
    Arena Vision ↗
    Elo Arena (texte)
    1 497,7
    Arena ↗

    Score components

    Value
    93,9/100
    Coding
    50,0/100
    Available model measurements
    93,9/100
    Vision
    90,9/100
  8. 08-

    gemini-3.8-flash-high

    gemini-3.8-flash-high

    92,9/100SANDBOX SCORE
    -

    Introduction

    Models

    gemini-3.8-flash-high

    Data

    SANDBOX score: 92,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#8

    1 editions in the Top 20 · best rank #8

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 583,5
    Arena WebDev ↗
    Elo Arena (vision)
    1 289,1
    Arena Vision ↗
    Elo Arena (texte)
    1 496,5
    Arena ↗

    Score components

    Value
    92,9/100
    Coding
    66,7/100
    Available model measurements
    92,9/100
    Vision
    80,3/100
  9. 09-

    muse-spark-1.3-max

    muse-spark-1.3-max

    91,9/100SANDBOX SCORE
    -

    Introduction

    Models

    muse-spark-1.3-max

    Data

    SANDBOX score: 91,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#9

    1 editions in the Top 20 · best rank #9

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 656,9
    Arena WebDev ↗
    Elo Arena (vision)
    1 289,7
    Arena Vision ↗
    Elo Arena (texte)
    1 494,2
    Arena ↗

    Score components

    Value
    91,9/100
    Coding
    86,4/100
    Available model measurements
    91,9/100
    Vision
    83,3/100
  10. 10-

    claude-opus-4-7

    claude-opus-4-7

    90,9/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-4-7

    Data

    SANDBOX score: 90,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#10

    1 editions in the Top 20 · best rank #10

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 555,2
    Arena WebDev ↗
    Elo Arena (search)
    1 233,3
    Arena Search ↗
    Elo Arena (vision)
    1 298,2
    Arena Vision ↗
    Elo Arena (texte)
    1 494,0
    Arena ↗

    Score components

    Value
    90,9/100
    Coding
    59,1/100
    Available model measurements
    90,9/100
    Search
    85,7/100
    Vision
    95,5/100
  11. 11-

    muse-spark-1.2 (xHigh)

    muse-spark-1.2 (xHigh)

    89,9/100SANDBOX SCORE
    -

    Introduction

    Models

    muse-spark-1.2 (xHigh)

    Data

    SANDBOX score: 89,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#11

    1 editions in the Top 20 · best rank #11

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 532,6
    Arena WebDev ↗
    Elo Arena (vision)
    1 292,9
    Arena Vision ↗
    Elo Arena (texte)
    1 492,0
    Arena ↗

    Score components

    Value
    89,9/100
    Coding
    47,0/100
    Available model measurements
    89,9/100
    Vision
    86,4/100
  12. 12-

    muse-spark-1.1

    muse-spark-1.1

    88,9/100SANDBOX SCORE
    -

    Introduction

    Models

    muse-spark-1.1

    Data

    SANDBOX score: 88,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#12

    1 editions in the Top 20 · best rank #12

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 542,1
    Arena WebDev ↗
    Elo Arena (vision)
    1 280,0
    Arena Vision ↗
    Elo Arena (texte)
    1 490,7
    Arena ↗

    Score components

    Value
    88,9/100
    Coding
    54,5/100
    Available model measurements
    88,9/100
    Vision
    60,6/100
  13. 13-

    claude-opus-5-high

    claude-opus-5-high

    87,9/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-5-high

    Data

    SANDBOX score: 87,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#13

    1 editions in the Top 20 · best rank #13

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 656,9
    Arena WebDev ↗
    Elo Arena (vision)
    1 287,4
    Arena Vision ↗
    Elo Arena (texte)
    1 490,1
    Arena ↗

    Score components

    Value
    87,9/100
    Coding
    87,9/100
    Available model measurements
    87,9/100
    Vision
    78,8/100
  14. 14-

    claude-opus-5-max

    claude-opus-5-max

    86,9/100SANDBOX SCORE
    -

    Introduction

    Models

    claude-opus-5-max

    Data

    SANDBOX score: 86,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#14

    1 editions in the Top 20 · best rank #14

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 691,3
    Arena WebDev ↗
    Elo Arena (texte)
    1 489,4
    Arena ↗

    Score components

    Value
    86,9/100
    Coding
    93,9/100
    Available model measurements
    86,9/100
  15. 15-

    muse-spark

    muse-spark

    85,9/100SANDBOX SCORE
    -

    Introduction

    Models

    muse-spark

    Data

    SANDBOX score: 85,9 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#15

    1 editions in the Top 20 · best rank #15

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (vision)
    1 293,9
    Arena Vision ↗
    Elo Arena (texte)
    1 488,9
    Arena ↗

    Score components

    Value
    85,9/100
    Available model measurements
    85,9/100
    Vision
    87,9/100
  16. 16-

    kimi-k3-max

    kimi-k3-max

    84,8/100SANDBOX SCORE
    -

    Introduction

    Models

    kimi-k3-max

    Data

    SANDBOX score: 84,8 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#16

    1 editions in the Top 20 · best rank #16

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 654,4
    Arena WebDev ↗
    Elo Arena (texte)
    1 488,1
    Arena ↗

    Score components

    Value
    84,8/100
    Coding
    84,8/100
    Available model measurements
    84,8/100
  17. 17-

    gemini-3.1-pro-preview

    gemini-3.1-pro-preview

    83,8/100SANDBOX SCORE
    -

    Introduction

    Models

    gemini-3.1-pro-preview

    Data

    SANDBOX score: 83,8 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#17

    1 editions in the Top 20 · best rank #17

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 446,7
    Arena WebDev ↗
    Elo Arena (vision)
    1 279,8
    Arena Vision ↗
    Elo Arena (texte)
    1 487,3
    Arena ↗

    Score components

    Value
    83,8/100
    Coding
    24,2/100
    Available model measurements
    83,8/100
    Vision
    59,1/100
  18. 18-

    gemini-3.7-flash-high

    gemini-3.7-flash-high

    82,8/100SANDBOX SCORE
    -

    Introduction

    Models

    gemini-3.7-flash-high

    Data

    SANDBOX score: 82,8 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#18

    1 editions in the Top 20 · best rank #18

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 591,5
    Arena WebDev ↗
    Elo Arena (vision)
    1 296,9
    Arena Vision ↗
    Elo Arena (texte)
    1 486,5
    Arena ↗

    Score components

    Value
    82,8/100
    Coding
    68,2/100
    Available model measurements
    82,8/100
    Vision
    92,4/100
  19. 19-

    gemini-3-pro

    gemini-3-pro

    81,8/100SANDBOX SCORE
    -

    Introduction

    Models

    gemini-3-pro

    Data

    SANDBOX score: 81,8 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#19

    1 editions in the Top 20 · best rank #19

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (WebDev)
    1 439,5
    Arena WebDev ↗
    Elo Arena (vision)
    1 289,3
    Arena Vision ↗
    Elo Arena (texte)
    1 485,5
    Arena ↗

    Score components

    Value
    81,8/100
    Coding
    22,7/100
    Available model measurements
    81,8/100
    Vision
    81,8/100
  20. 20-

    gpt-5.6-sol-xhigh

    gpt-5.6-sol-xhigh

    80,8/100SANDBOX SCORE
    -

    Introduction

    Models

    gpt-5.6-sol-xhigh

    Data

    SANDBOX score: 80,8 out of 100.

    30 DAYS MOMENTUM

    History is being collected
    W41#20

    1 editions in the Top 20 · best rank #20

    Open profile ↗
    Measurements, score components and sources
    Elo Arena (search)
    1 257,3
    Arena Search ↗
    Elo Arena (vision)
    1 287,0
    Arena Vision ↗
    Elo Arena (texte)
    1 485,1
    Arena ↗

    Score components

    Value
    80,8/100
    Available model measurements
    80,8/100
    Search
    100,0/100
    Vision
    77,3/100