Gemini 3.6 Flash

{
  "id": "google/gemini-3.6-flash",
  "name": "Gemini 3.6 Flash",
  "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
  "family": "gemini-flash",
  "last_updated": "2026-07-21",
  "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": "SWE-Bench Pro",
      "score": 58.7,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "resolve rate",
      "harness": "Antigravity",
      "date": "2026-07-21"
    },
    {
      "name": "DeepSWE",
      "score": 49,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "resolve rate",
      "variant": "high reasoning",
      "version": "1.1",
      "date": "2026-07-21"
    },
    {
      "name": "Terminal-Bench",
      "score": 78,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "accuracy",
      "harness": "Terminus 2",
      "version": "2.1",
      "date": "2026-07-21"
    },
    {
      "name": "MLE-Bench",
      "score": 63.9,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "average position score",
      "dataset": "Partial 30",
      "date": "2026-07-21"
    },
    {
      "name": "GDPval-AA",
      "score": 1421,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "Elo",
      "version": "v2",
      "date": "2026-07-21"
    },
    {
      "name": "OSWorld-Verified",
      "score": 83,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "success rate",
      "date": "2026-07-21"
    },
    {
      "name": "CharXiv Reasoning",
      "score": 85.2,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "accuracy",
      "variant": "no tools",
      "date": "2026-07-21"
    },
    {
      "name": "CharXiv Reasoning",
      "score": 89.4,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "accuracy",
      "variant": "with tools",
      "date": "2026-07-21"
    },
    {
      "name": "GDM-MRCR",
      "score": 91.8,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "accuracy",
      "variant": "128k average, 8-needle",
      "version": "v2",
      "date": "2026-07-21"
    },
    {
      "name": "GDM-MRCR",
      "score": 54,
      "source": "https://deepmind.google/models/evals-methodology/gemini-3-6-flash/",
      "metric": "accuracy",
      "variant": "1M pointwise, 8-needle",
      "version": "v2",
      "date": "2026-07-21"
    }
  ],
  "release_date": "2026-07-21",
  "open_weights": false
}