{
  "notice": "Please credit \"Is software solved?\" and the sources listed in credits when you reuse these numbers. They are our own aggregates. For original records, go to each source.",
  "id": "model-opinions",
  "name": "What AI models say",
  "question": "Do AI models think software is solved?",
  "metric": "Median answer from AI models asked to score it from 0% to 100%",
  "solvedIf": "Models say it is close to 100%",
  "value": "20%",
  "trend": [
    {
      "label": "GPT-4",
      "value": 35
    },
    {
      "label": "Mistral Large",
      "value": 15
    },
    {
      "label": "GPT-4o",
      "value": 40
    },
    {
      "label": "Llama 3.1 8B Instruct",
      "value": 20
    },
    {
      "label": "Llama 3.3 70B Instruct",
      "value": 20
    },
    {
      "label": "DeepSeek V3",
      "value": 20
    },
    {
      "label": "Llama 4 Maverick",
      "value": 20
    },
    {
      "label": "Gemini 2.5 Flash",
      "value": 5
    },
    {
      "label": "GPT-5",
      "value": 20
    },
    {
      "label": "Claude Sonnet 4.6",
      "value": 18
    },
    {
      "label": "GPT-5.5",
      "value": 30
    },
    {
      "label": "Claude Opus 4.8",
      "value": 15
    },
    {
      "label": "Gemini 3.8 Flash",
      "value": 20
    },
    {
      "label": "DeepSeek V4.1 Flash",
      "value": 20
    },
    {
      "label": "Grok 4.7",
      "value": 25
    },
    {
      "label": "Claude Opus 5.5",
      "value": 35
    },
    {
      "label": "GPT-6 Sol",
      "value": 30
    },
    {
      "label": "Claude Sonnet 5.5",
      "value": 22
    },
    {
      "label": "GPT-6.1 Sol",
      "value": 25
    },
    {
      "label": "Gemini 4 Argon",
      "value": 25
    }
  ],
  "trendScale": "category",
  "trendLabel": "Each model's median answer, in percent, ordered by release date. These are opinions, not measurements.",
  "caution": [
    "This is opinion, not evidence, so it does not affect the solved score. An answer reflects a model's training data and tuning, and the companies selling AI built these models.",
    "Older models only know the world up to their training date, and each model answered just three times. Different wording could change these scores."
  ],
  "prompt": "Is software solved?\n\nBy \"solved\" I mean that AI can do nearly all the software engineering work humans do today, including deciding what to build, writing it, running it and fixing it, with little human oversight and at low cost, so that few human software engineers are still needed.\n\nGive your honest assessment of how close the world is to that today, as far as you know.\n\nReply with JSON only, in this exact format:\n{\"score\": <a whole number from 0 to 100, where 0 means not at all and 100 means fully solved>, \"reason\": \"<one sentence>\"}",
  "analysis": {
    "title": "Answers by model",
    "intro": "Each model was asked once, most recently on Nov 1, 2026. Oldest model first. No model scored above 40%.",
    "points": [
      "GPT-4 (2023-05-28): 35%.",
      "Mistral Large (2024-02-26): 15%.",
      "GPT-4o (2024-05-13): 40%.",
      "Llama 3.1 8B Instruct (2024-07-23): 20%.",
      "Llama 3.3 70B Instruct (2024-12-06): 20%.",
      "DeepSeek V3 (2024-12-26): 20%.",
      "Llama 4 Maverick (2025-04-05): 20%.",
      "Gemini 2.5 Flash (2025-06-17): 5%.",
      "GPT-5 (2025-08-07): 20%.",
      "Claude Sonnet 4.6 (2026-02-17): 18%.",
      "GPT-5.5 (2026-04-24): 30%.",
      "Claude Opus 4.8 (2026-05-27): 15%.",
      "Gemini 3.8 Flash (2026-09-02): 20%.",
      "DeepSeek V4.1 Flash (2026-09-10): 20%.",
      "Grok 4.7 (2026-09-21): 25%.",
      "Claude Opus 5.5 (2026-09-22): 35%.",
      "GPT-6 Sol (2026-09-22): 30%.",
      "Claude Sonnet 5.5 (2026-09-28): 22%.",
      "GPT-6.1 Sol (2026-09-29): 25%.",
      "Gemini 4 Argon (2026-10-13): 25%."
    ]
  },
  "status": "Say not yet",
  "rule": "Say not yet when the median answer is under 50.",
  "direction": "away",
  "checks": [
    {
      "date": "2026-11-02",
      "value": "20%",
      "status": "Say not yet"
    },
    {
      "date": "2026-11-01",
      "value": "20%",
      "status": "Say not yet"
    }
  ],
  "url": "/signals/model-opinions",
  "api": "/api/signals/model-opinions.json",
  "credits": [
    {
      "name": "Our survey of AI models",
      "url": "https://openrouter.ai/models",
      "signal": "model-opinions",
      "license": "Our own run",
      "credit": "Our own survey of AI models, run through OpenRouter."
    }
  ]
}