Gemini 3.5 Flash

{
  "id": "google/gemini-3.5-flash",
  "name": "Gemini 3.5 Flash",
  "description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
  "family": "gemini-flash",
  "last_updated": "2026-05-19",
  "knowledge": "2025-01",
  "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": "Terminal-Bench",
      "score": 76.2,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "success rate",
      "harness": "Terminus-2",
      "version": "2.1",
      "date": "2026-05-19"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 55.1,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "resolve rate",
      "variant": "single attempt",
      "dataset": "public",
      "date": "2026-05-19"
    },
    {
      "name": "MCP Atlas",
      "score": 83.6,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "success rate",
      "date": "2026-05-19"
    },
    {
      "name": "Toolathlon",
      "score": 56.5,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "success rate",
      "date": "2026-05-19"
    },
    {
      "name": "OSWorld-Verified",
      "score": 78.4,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "success rate",
      "date": "2026-05-19"
    },
    {
      "name": "MMMU Pro",
      "score": 83.6,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "variant": "no tools",
      "date": "2026-05-19"
    },
    {
      "name": "CharXiv Reasoning",
      "score": 84.2,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "variant": "no tools",
      "date": "2026-05-19"
    },
    {
      "name": "Humanity's Last Exam",
      "score": 40.2,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "dataset": "full set, text + MM",
      "date": "2026-05-19"
    },
    {
      "name": "ARC-AGI-2",
      "score": 72.1,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "date": "2026-05-19"
    },
    {
      "name": "GDPval-AA",
      "score": 1656,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "Elo",
      "date": "2026-05-19"
    }
  ],
  "release_date": "2026-05-19",
  "open_weights": false
}