Gemini 3.7 Flash

{
  "id": "google/gemini-3.7-flash",
  "name": "Gemini 3.7 Flash",
  "description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
  "family": "gemini-flash",
  "last_updated": "2026-08-13",
  "knowledge": "2026-03",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video",
      "audio",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1048576,
    "output": 65536
  },
  "benchmarks": [
    {
      "name": "FrontierCode",
      "score": 43.6,
      "source": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
      "metric": "score",
      "version": "1.1 Main",
      "date": "2026-08-13"
    },
    {
      "name": "DeepSWE",
      "score": 65.3,
      "source": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
      "metric": "resolve rate",
      "version": "1.1",
      "date": "2026-08-13"
    },
    {
      "name": "Terminal-Bench",
      "score": 85.8,
      "source": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
      "metric": "accuracy",
      "version": "2.1",
      "date": "2026-08-13"
    },
    {
      "name": "AutomationBench",
      "score": 30.4,
      "source": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
      "metric": "accuracy",
      "dataset": "private set",
      "date": "2026-08-13"
    },
    {
      "name": "GDP.pdf",
      "score": 34,
      "source": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
      "metric": "accuracy",
      "date": "2026-08-13"
    },
    {
      "name": "GDM-MRCR",
      "score": 97,
      "source": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
      "metric": "accuracy",
      "variant": "128k average, 8-needle",
      "version": "v2",
      "date": "2026-08-13"
    }
  ],
  "release_date": "2026-08-13",
  "open_weights": false
}