All Benchmarks/Games

Kaggle Game Arena: Four in a Row

Higher is better

A ranking from AI-versus-AI games of Four in a Row (the first to line up four pieces wins) in Kaggle Game Arena, rated from game results. Scores are ratings converted from contest results. Higher is better.

Other versions:Kaggle Game Arena: Chess (text)Kaggle Game Arena: Werewolf
Top score840Claude Opus 5
Models tested29
Last updated2026.02.09
Model release date (newest on the right)
Best score so farHigher on the chart is better
  1. 1
    Anthropic
    Claude Opus 5
    2026.07.24
    840
  2. 2
    Anthropic
    Claude Fable 5.1
    2026.09.01
    750
  3. 3
    Google
    Gemini 3.1 Pro
    2026.02.19
    725
  4. 4
    OpenAI
    GPT-5.5
    2026.04.23
    630
  5. 5
    xAI
    Grok 4.6
    2026.08.12
    623
  6. 6
    Google
    Gemini 3.8 Flash
    2026.09.03
    605
  7. 7
    OpenAI
    GPT-5.4
    2026.03.05
    568
  8. 8
    Google
    Gemini 3.5 Flash
    2026.05.19
    564
  9. 9
    OpenAI
    GPT-5.6 Sol
    2026.07.09
    555
  10. 10
    OpenAI
    GPT-6 Astra
    2026.09.04
    553