OpenGPTEvidence-based model decisions
Start evaluationMy Radar

July 2026 · Research edition

AI model rankings

Compare exact model configurations across independent user-preference, intelligence, objective-task, cost, and open-weight-model rankings—then test two on your own work.

Start with your taskCompare two leading modelsLatest model changes
Data from published evaluationsPublished: Jul 24, 2026 · 3 independent public sources

OpenGPT organizes and presents publicly released third-party evaluation data; it did not rerun these model tests. Use the rankings to understand relative performance, then validate candidates on your own work.

Ranking method
Published
Jul 24, 2026
Data cutoff
Jul 24, 2026
Method
OpenGPT research synthesis 1.1
Ranking basis
3 independent public sources

July 2026 · Research edition

Choose a ranking metric

378 source-listed model entries

Start with the decision you need to make. Each scenario opens the most relevant published ranking signal. The original source and scale remain visible.

Choose what to show

Show every publisher record with its source model ID or source name, including aliases and run configurations. Source ranks are preserved; ties can still cause rank numbers to skip.

User preference score

LMArena’s complete latest style-controlled overall ranking. Every publisher record keeps its source model ID; a provider-documented model ID appears separately when available.

Independent sourceLMArenaData retrieved: Jul 24, 2026
Leaderboard publication date
Jul 21, 2026
Ranking scope
Text responses · Style-controlled · Overall ranking
Data retrieved
Jul 24, 2026
Original ranking ↗Scoring method ↗

Compared with previous edition Jun 25, 2026. Same source and method. Rank movement is relative; it does not by itself prove a change in model quality.

Showing 40 of 378. User preference score.

  1. Rank 1

    claude-fable-5

    Anthropic
    Model ID
    claude-fable-5
    Votes cast
    14,646
    License type
    Closed / proprietaryProprietary
    User preference score1507Based on anonymous head-to-head comparisons
    Likely score range1,500.9–1,513.7
    Model detailsReview match evidenceView source
  2. Rank 2

    claude-opus-4-6-thinking

    Anthropic
    Model ID
    claude-opus-4-6
    Votes cast
    63,191
    License type
    Closed / proprietaryProprietary
    User preference score1505Based on anonymous head-to-head comparisons
    Likely score range1,501.1–1,508.6
    Model detailsReview match evidenceView source
  3. Rank 3

    claude-opus-4-7-thinking

    Anthropic
    Model ID
    claude-opus-4-7
    Votes cast
    50,683
    License type
    Closed / proprietaryProprietary
    User preference score1502Based on anonymous head-to-head comparisons
    Likely score range1,497.8–1,506.2
    Model detailsReview match evidenceView source
  4. Rank 4

    claude-opus-4-6

    Anthropic
    Model ID
    claude-opus-4-6
    Votes cast
    67,037
    License type
    Closed / proprietaryProprietary
    User preference score1498Based on anonymous head-to-head comparisons
    Likely score range1,494.1–1,501.4
    Model detailsReview match evidenceView source
  5. Rank 5

    muse-spark-1.1

    Meta
    Model ID
    muse-spark-1.1
    Votes cast
    7,927
    License type
    Closed / proprietaryProprietary
    User preference score1495Based on anonymous head-to-head comparisons
    Likely score range1,487.8–1,502.3
    Model detailsReview match evidenceView source
  6. Rank 6

    claude-opus-4-7

    Anthropic
    Model ID
    claude-opus-4-7
    Votes cast
    51,788
    License type
    Closed / proprietaryProprietary
    User preference score1494Based on anonymous head-to-head comparisons
    Likely score range1,489.5–1,497.9
    Model detailsReview match evidenceView source
  7. Rank 7

    muse-spark

    Meta
    Model ID
    muse-spark
    Votes cast
    13,565
    License type
    Closed / proprietaryProprietary
    User preference score1488Based on anonymous head-to-head comparisons
    Likely score range1,481.7–1,493.4
    Model detailsReview match evidenceView source
  8. Rank 8

    gemini-3.1-pro-preview

    Google
    Model ID
    gemini-3.1-pro-preview
    Votes cast
    84,631
    License type
    Closed / proprietaryProprietary
    User preference score1486Based on anonymous head-to-head comparisons
    Likely score range1,482.3–1,489.3
    Model detailsReview match evidenceView source
  9. Rank 9

    gemini-3-pro

    Google
    Source model ID
    gemini-3-pro
    Votes cast
    41,268
    License type
    Closed / proprietaryProprietary
    User preference score1486Based on anonymous head-to-head comparisons
    Likely score range1,481.9–1,489.6
    Model detailsView source
  10. Rank 10

    kimi-k3

    Moonshot AI
    Model ID
    kimi-k3
    Votes cast
    3,619
    License type
    Closed / proprietaryProprietary
    User preference score1486Based on anonymous head-to-head comparisons
    Likely score range1,475.7–1,495.6
    Model detailsReview match evidenceView source
  11. Rank 11

    gpt-5.6-sol-xhigh

    OpenAI
    Model ID
    gpt-5.6-sol
    Votes cast
    6,221
    License type
    Closed / proprietaryProprietary
    User preference score1485Based on anonymous head-to-head comparisons
    Likely score range1,477.2–1,493.0
    Model detailsReview match evidenceView source
  12. Rank 12

    gemini-3.6-flash

    Google
    Model ID
    gemini-3.6-flash
    Votes cast
    4,747
    License type
    Closed / proprietaryProprietary
    User preference score1485Based on anonymous head-to-head comparisons
    Likely score range1,476.2–1,493.9
    Model detailsReview match evidenceView source
  13. Rank 13

    claude-opus-4-8-thinking

    Anthropic
    Model ID
    claude-opus-4-8
    Votes cast
    30,901
    License type
    Closed / proprietaryProprietary
    User preference score1484Based on anonymous head-to-head comparisons
    Likely score range1,478.5–1,488.7
    Model detailsReview match evidenceView source
  14. Rank 14

    gpt-5.5-high

    OpenAI
    Source model ID
    gpt-5.5-high
    Votes cast
    45,760
    License type
    Closed / proprietaryProprietary
    User preference score1482Based on anonymous head-to-head comparisons
    Likely score range1,477.3–1,486.1
    Model detailsView source
  15. Rank 15

    gpt-5.4-high

    OpenAI
    Model ID
    gpt-5.4
    Votes cast
    58,997
    License type
    Closed / proprietaryProprietary
    User preference score1478Based on anonymous head-to-head comparisons
    Likely score range1,473.8–1,481.7
    Model detailsReview match evidenceView source
  16. Rank 16

    gpt-5.5

    OpenAI
    Source model ID
    gpt-5.5
    Votes cast
    47,180
    License type
    Closed / proprietaryProprietary
    User preference score1476Based on anonymous head-to-head comparisons
    Likely score range1,472.0–1,480.7
    Model detailsView source
  17. Rank 17

    gemini-3.5-flash-high

    Google
    Model ID
    gemini-3.5-flash
    Votes cast
    10,092
    License type
    Closed / proprietaryProprietary
    User preference score1476Based on anonymous head-to-head comparisons
    Likely score range1,469.7–1,482.8
    Model detailsReview match evidenceView source
  18. Rank 18

    gpt-5.2-chat-latest-20260210

    OpenAI
    Source model ID
    gpt-5.2-chat-latest-20260210
    Votes cast
    34,420
    License type
    Closed / proprietaryProprietary
    User preference score1476Based on anonymous head-to-head comparisons
    Likely score range1,471.6–1,479.8
    Model detailsView source
  19. Rank 19

    qwen3.7-max-preview

    Alibaba
    Source model ID
    qwen3.7-max-preview
    Votes cast
    3,714
    License type
    Closed / proprietaryProprietary
    User preference score1475Based on anonymous head-to-head comparisons
    Likely score range1,465.1–1,485.2
    Model detailsView source
  20. Rank 20

    grok-4.20-beta1

    xAI
    Source model ID
    grok-4.20-beta1
    Votes cast
    26,822
    License type
    Closed / proprietaryProprietary
    User preference score1474Based on anonymous head-to-head comparisons
    Likely score range1,469.7–1,479.0
    Model detailsView source
  21. Rank 21

    gemini-3.5-flash-medium

    Google
    Model ID
    gemini-3.5-flash
    Votes cast
    14,063
    License type
    Closed / proprietaryProprietary
    User preference score1474Based on anonymous head-to-head comparisons
    Likely score range1,468.2–1,480.4
    Model detailsReview match evidenceView source
  22. Rank 22

    claude-opus-4-8

    Anthropic
    Model ID
    claude-opus-4-8
    Votes cast
    31,619
    License type
    Closed / proprietaryProprietary
    User preference score1473Based on anonymous head-to-head comparisons
    Likely score range1,468.3–1,478.5
    Model detailsReview match evidenceView source
  23. Rank 23

    gpt-5.5-instant

    OpenAI
    Source model ID
    gpt-5.5-instant
    Votes cast
    25,995
    License type
    Closed / proprietaryProprietary
    User preference score1473Based on anonymous head-to-head comparisons
    Likely score range1,468.2–1,478.5
    Model detailsView source
  24. Rank 24

    grok-4.20-beta-0309-reasoning

    xAI
    Model ID
    grok-4.20-0309-reasoning
    Votes cast
    60,330
    License type
    Closed / proprietaryProprietary
    User preference score1473Based on anonymous head-to-head comparisons
    Likely score range1,469.3–1,477.0
    Model detailsReview match evidenceView source
  25. Rank 25

    gemini-3-flash

    Google
    Source model ID
    gemini-3-flash
    Votes cast
    30,682
    License type
    Closed / proprietaryProprietary
    User preference score1473Based on anonymous head-to-head comparisons
    Likely score range1,468.7–1,477.5
    Model detailsView source
  26. Rank 26

    claude-opus-4-5-20251101-thinking-32k

    Anthropic
    Source model ID
    claude-opus-4-5-20251101-thinking-32k
    Votes cast
    37,037
    License type
    Closed / proprietaryProprietary
    User preference score1473Based on anonymous head-to-head comparisons
    Likely score range1,469.0–1,476.8
    Model detailsView source
  27. Rank 27

    claude-sonnet-4-6

    Anthropic
    Source model ID
    claude-sonnet-4-6
    Votes cast
    57,183
    License type
    Closed / proprietaryProprietary
    User preference score1473Based on anonymous head-to-head comparisons
    Likely score range1,468.7–1,476.4
    Model detailsView source
  28. Rank 28

    grok-4.20-multi-agent-beta-0309

    xAI
    Source model ID
    grok-4.20-multi-agent-beta-0309
    Votes cast
    59,116
    License type
    Closed / proprietaryProprietary
    User preference score1471Based on anonymous head-to-head comparisons
    Likely score range1,467.1–1,474.8
    Model detailsView source
  29. Rank 29

    glm-5.1

    Z.AI
    Source model ID
    glm-5.1
    Votes cast
    30,726
    License type
    MIT
    User preference score1470Based on anonymous head-to-head comparisons
    Likely score range1,465.1–1,474.2
    Model detailsView source
  30. Rank 30

    glm-5.2 (max)

    Z.AI
    Source model ID
    glm-5.2 (max)
    Votes cast
    18,017
    License type
    MIT
    User preference score1469Based on anonymous head-to-head comparisons
    Likely score range1,463.4–1,475.0
    Model detailsView source
  31. Rank 31

    claude-opus-4-5-20251101

    Anthropic
    Source model ID
    claude-opus-4-5-20251101
    Votes cast
    70,976
    License type
    Closed / proprietaryProprietary
    User preference score1469Based on anonymous head-to-head comparisons
    Likely score range1,465.9–1,472.3
    Model detailsView source
  32. Rank 32

    ernie-5.1

    Baidu
    Source model ID
    ernie-5.1
    Votes cast
    37,418
    License type
    Closed / proprietaryProprietary
    User preference score1468Based on anonymous head-to-head comparisons
    Likely score range1,463.1–1,472.4
    Model detailsView source
  33. Rank 33

    grok-4.5

    xAI
    Model ID
    grok-4.5
    Votes cast
    7,833
    License type
    Closed / proprietaryProprietary
    User preference score1468Based on anonymous head-to-head comparisons
    Likely score range1,460.4–1,475.0
    Model detailsReview match evidenceView source
  34. Rank 34

    mimo-v2.5-pro

    Xiaomi
    Source model ID
    mimo-v2.5-pro
    Votes cast
    42,195
    License type
    MIT
    User preference score1467Based on anonymous head-to-head comparisons
    Likely score range1,462.4–1,471.3
    Model detailsView source
  35. Rank 35

    gpt-5.4

    OpenAI
    Model ID
    gpt-5.4
    Votes cast
    62,036
    License type
    Closed / proprietaryProprietary
    User preference score1466Based on anonymous head-to-head comparisons
    Likely score range1,462.4–1,470.1
    Model detailsReview match evidenceView source
  36. Rank 36

    grok-4.1-thinking

    xAI
    Source model ID
    grok-4.1-thinking
    Votes cast
    65,461
    License type
    Closed / proprietaryProprietary
    User preference score1466Based on anonymous head-to-head comparisons
    Likely score range1,462.7–1,469.1
    Model detailsView source
  37. Rank 37

    qwen3.5-max-preview

    Alibaba
    Source model ID
    qwen3.5-max-preview
    Votes cast
    21,479
    License type
    Closed / proprietaryProprietary
    User preference score1465Based on anonymous head-to-head comparisons
    Likely score range1,459.8–1,469.8
    Model detailsView source
  38. Rank 38

    claude-sonnet-5-high

    Anthropic
    Model ID
    claude-sonnet-5
    Votes cast
    13,521
    License type
    Closed / proprietaryProprietary
    User preference score1461Based on anonymous head-to-head comparisons
    Likely score range1,454.9–1,467.4
    Model detailsReview match evidenceView source
  39. Rank 39

    kimi-k2.6

    Moonshot AI
    Model ID
    kimi-k2.6
    Votes cast
    37,686
    License type
    Modified MIT
    User preference score1461Based on anonymous head-to-head comparisons
    Likely score range1,456.4–1,465.5
    Model detailsReview match evidenceView source
  40. Rank 40

    qwen3.6-max-preview

    Alibaba
    Source model ID
    qwen3.6-max-preview
    Votes cast
    5,188
    License type
    Closed / proprietaryProprietary
    User preference score1460Based on anonymous head-to-head comparisons
    Likely score range1,451.7–1,468.5
    Model detailsView source
Showing 40 of 378
Ranking methodEach view preserves the source’s metric, release, and methodology. Follow the links to audit the underlying work.

Ranking basis

Full published ranking and official model IDs

The main ranking preserves every publisher record and shows its source model ID or source name. Every row can be compared: exact, configuration-safe mappings use official versions; all other rows stay within one source ranking. Missing data never becomes a zero score.
79 official model IDs
79
43 with public ranking data
43
36 awaiting comparable data
36
378 source records retained for audit
378
Model directory

Ranking basis

How to read this research edition

  • Scores stay on their original publisher scales. They are not combined into a composite score.

  • Missing data does not mean zero. It means the publisher did not report that metric for this snapshot.

  • When a source reports model settings, the position applies to that exact setup and source release—not every task, region, or deployment.

  • No provider can pay for placement. OpenGPT links directly to the evidence used.

Ranking basis

Data and sources

Each view preserves the source’s metric, release, and methodology. Follow the links to audit the underlying work.
AR

LMArena

The complete latest style-controlled overall ranking, based on users comparing two model answers side by side.

Leaderboard publication date
Jul 21, 2026
Data retrieved
Jul 24, 2026
License
CC BY 4.0

Original ranking ↗Scoring method ↗

AA

Artificial Analysis

Nine evaluations across agentic work, coding, general knowledge, and scientific reasoning.

Source snapshot
Intelligence Index v4.1 · continuously updated
Data retrieved
Jul 24, 2026

Original ranking ↗Scoring method ↗

LB

LiveBench

Twenty-three objective tasks across seven categories; questions refresh every six months.

Source snapshot
LiveBench-2026-06-25
Data retrieved
Jul 24, 2026

Original ranking ↗Scoring method ↗

Method

A predictable publishing rhythm

OpenGPT will separate changing signals from frozen editions so past decisions remain auditable.
  1. 01

    Weekly watch

    Review new model and benchmark releases; flag material changes without silently rewriting this edition.

  2. 02

    Monthly frozen edition

    Publish a dated snapshot with exact configurations, source releases, and corrections.

  3. 03

    Quarterly method review

    Review categories, source quality, conflicts, and inclusion rules before changing the method.