{
  "id": 14160181,
  "title": "Which model should Dory run on? We tested eight on real questions",
  "url": "https://urgent.news/2026/10/13/which-model-should-dory-run-on-we-tested-eight-on-real-questions",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T09:05:10.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/playtomic/which-model-should-dory-run-on-we-tested-eight-on-real-questions-3dkm"
  },
  "original_language": "en",
  "account": "Playtomic's internal AI agent, Dory, was put to the test against eight different AI models, with two AI judges from different companies evaluating each answer. The models included GPT-5.6 Terra Pro from OpenAI, Claude Sonnet 5.5 and Claude Haiku 5.5 from Anthropic, Gemini 3.8 Flash from Google, GLM 5.3 and DeepSeek V4 Pro from Chinese labs, and Mistral Large 4 from Europe. The ultimate goal was to find which model best answers the real questions Dory receives, while keeping the cost and speed in mind.",
  "summary": "We put eight new AI models through the questions people actually ask Dory, Playtomic's internal AI agent, and had two AI judges from different companies check every answer against the code and the data. Meet Dory Dory is Playtomic's AI agent for the whole company, and it lives in Slack. Engineers use it a lot, but most of the people asking it things work in customer care, product, marketing and…",
  "key_points": [
    "Dory, Playtomic's internal AI agent, tested against eight AI models",
    "Two independent AI judges evaluated each model's answers",
    "Models included GPT-5.6 Terra Pro, Claude Sonnet 5.5, Gemini 3.8 Flash"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}