Compare language models

DeepSWE

  • Claude Fable 5
  • Claude Opus 5
  • Gemini 3.8 Flash
  • GLM-5.3
  • GPT-5.6 Sol
  • GPT-5.6 Terra
  • GPT-6 Astra
  • Grok 4.6
  • Kimi K3

2D chart, two axes

Loading model data