Gemini 3.1 Pro Preview

{
  "id": "google/gemini-3.1-pro-preview",
  "name": "Gemini 3.1 Pro Preview",
  "description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
  "family": "gemini-pro",
  "last_updated": "2026-02-19",
  "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": "SWE-Bench Pro",
      "score": 54.2,
      "source": "https://www.anthropic.com/news/claude-opus-4-8",
      "metric": "resolve rate",
      "date": "2026-05-28"
    },
    {
      "name": "Terminal-Bench",
      "score": 70.3,
      "source": "https://www.anthropic.com/news/claude-opus-4-8",
      "metric": "success rate",
      "harness": "Terminus-2",
      "version": "2.1",
      "date": "2026-05-28"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 46.1,
      "source": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
      "metric": "resolve rate",
      "dataset": "public"
    },
    {
      "name": "SWE-Atlas Codebase QnA",
      "score": 13.5,
      "source": "https://labs.scale.com/leaderboard/sweatlas-qna",
      "metric": "score",
      "harness": "Mini-SWE-Agent"
    },
    {
      "name": "SWE-Atlas Refactoring",
      "score": 33.81,
      "source": "https://labs.scale.com/leaderboard/sweatlas-refactoring",
      "metric": "score",
      "harness": "Gemini CLI"
    },
    {
      "name": "SWE-Atlas Test Writing",
      "score": 29.84,
      "source": "https://labs.scale.com/leaderboard/sweatlas-tw",
      "metric": "score",
      "harness": "Mini-SWE-Agent"
    },
    {
      "name": "Artificial Analysis Coding Agent Index",
      "score": 43,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "average pass@1",
      "harness": "Gemini CLI",
      "variant": "high"
    },
    {
      "name": "SWE-Atlas Codebase QnA",
      "score": 45.6,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "pass@1",
      "harness": "Gemini CLI",
      "variant": "high"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 15.1,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "pass@1",
      "harness": "Gemini CLI",
      "variant": "high",
      "dataset": "hard-aa"
    },
    {
      "name": "Terminal-Bench",
      "score": 68.3,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "pass@1",
      "harness": "Gemini CLI",
      "variant": "high",
      "version": "2.1"
    },
    {
      "name": "GPQA Diamond",
      "score": 94.3,
      "source": "https://openai.com/index/introducing-gpt-5-5/",
      "metric": "accuracy",
      "date": "2026-04-23"
    },
    {
      "name": "Humanity's Last Exam",
      "score": 44.4,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "dataset": "full set, text + MM",
      "date": "2026-05-19"
    },
    {
      "name": "ARC-AGI-2",
      "score": 77.1,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "date": "2026-05-19"
    },
    {
      "name": "MMMU Pro",
      "score": 80.5,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "variant": "no tools",
      "date": "2026-05-19"
    },
    {
      "name": "MCP Atlas",
      "score": 78.2,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "success rate",
      "date": "2026-05-19"
    },
    {
      "name": "OSWorld-Verified",
      "score": 76.2,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "success rate",
      "date": "2026-05-19"
    },
    {
      "name": "CharXiv Reasoning",
      "score": 83.3,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "accuracy",
      "variant": "no tools",
      "date": "2026-05-19"
    },
    {
      "name": "GDPval-AA",
      "score": 1314,
      "source": "https://deepmind.google/models/gemini/flash/",
      "metric": "Elo",
      "date": "2026-05-19"
    }
  ],
  "release_date": "2026-02-19",
  "open_weights": false
}