Kimi K2.6

{
  "id": "moonshotai/kimi-k2.6",
  "name": "Kimi K2.6",
  "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
  "family": "kimi-k2",
  "last_updated": "2026-04-21",
  "knowledge": "2025-01",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 262144
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Verified",
      "score": 80.2,
      "source": "https://huggingface.co/moonshotai/Kimi-K2.6",
      "metric": "resolved"
    },
    {
      "name": "Artificial Analysis Coding Agent Index",
      "score": 50.5,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "average pass@1",
      "harness": "Claude Code"
    },
    {
      "name": "SWE-Atlas Codebase QnA",
      "score": 59.8,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "pass@1",
      "harness": "Claude Code"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 27.3,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "pass@1",
      "harness": "Claude Code",
      "dataset": "hard-aa"
    },
    {
      "name": "Terminal-Bench",
      "score": 64.3,
      "source": "https://artificialanalysis.ai/agents/coding-agents",
      "metric": "pass@1",
      "harness": "Claude Code",
      "version": "2.1"
    }
  ],
  "release_date": "2026-04-21",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/moonshotai/Kimi-K2.6"
    }
  ]
}