{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-26",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "minimax-m3-1-flash",
    "name": "MiniMax M3.1 Flash",
    "lab": "minimax",
    "date": "2026-10-19",
    "source": "https://www.minimax.io/blog/minimax-m31f",
    "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
    "releases": [],
    "variant_of": null,
    "made_by": "MiniMax",
    "url": "https://frontierlog.ai/model/minimax-m3-1-flash",
    "results": [
      {
        "id": "minimax-m3-1-flash:automationbench:default:1",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 62.8,
        "unit": "%",
        "printed": "62.8",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax M3.1 Flash",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "benchmark table image (first image), row 'Automation-Bench v1.0.6', column 'MiniMax M3.1 Flash'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "AutomationBench v1.0.6; 600 public tasks",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
      },
      {
        "id": "minimax-m3-1-flash:terminal-bench-4-0:default:1",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "terminal-bench-4-0",
        "benchmark_name": "Terminal-Bench 4.0",
        "setting": "default",
        "setting_name": "",
        "score": 38.1,
        "unit": "%",
        "printed": "38.1",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax M3.1 Flash",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "benchmark table image (first image), row 'Terminal Bench 4.0', column 'MiniMax M3.1 Flash'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Codex 0.149.1 harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
      },
      {
        "id": "minimax-m3-1-flash:osworld-2-0:offline-partial:1",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "osworld-2-0",
        "benchmark_name": "OSWorld 2.0",
        "setting": "offline-partial",
        "setting_name": "Offline set, partial score",
        "score": 61.7,
        "unit": "%",
        "printed": "61.7",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax M3.1 Flash",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "benchmark table image (first image), row 'OSWorld 2.0', column 'MiniMax M3.1 Flash'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "task release v2026.08.08",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
      },
      {
        "id": "minimax-m3-1-flash:deepswe-1-1:default:1",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 73.7,
        "unit": "%",
        "printed": "73.7",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax M3.1 Flash",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "benchmark table image (first image), row 'DeepSWE v1.1', column 'MiniMax M3.1 Flash'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "mini-SWE-agent 2.4.5 harness; 512K context",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
      },
      {
        "id": "minimax-m3-1-flash:cybergym:default:1",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "cybergym",
        "benchmark_name": "CyberGym",
        "setting": "default",
        "setting_name": "",
        "score": 82.2,
        "unit": "%",
        "printed": "82.2",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax M3.1 Flash",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "benchmark table image (first image), row 'CyberGym', column 'MiniMax M3.1 Flash'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code 2.1.263 harness; 1M context",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
      },
      {
        "id": "minimax-m3-1-flash:hle:no-tools:1",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 43.4,
        "unit": "%",
        "printed": "43.4",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax M3.1 Flash",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "benchmark table image (first image), row 'HLE (w/o tools)', column 'MiniMax M3.1 Flash'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "text-only subset",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/5525d0bcceba0858.m31-flash-en-2-1792403273121-webp",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-2-1792403273121-webp-1.m31-flash-en-2-1792403273121-webp"
      },
      {
        "id": "minimax-m3-1-flash:automationbench:default:2",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 52.8,
        "unit": "%",
        "printed": "52.8%",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax-M3.1-Flash (low)",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "chart image 'Automation-Bench Score vs. Cost per Task (USD)', MiniMax-M3.1-Flash line, point labelled 'low'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "low effort; AutomationBench v1.0.6; Claude Code harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/2fe56b1cefe6f716.png",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-5-1792403273121.png"
      },
      {
        "id": "minimax-m3-1-flash:automationbench:default:3",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 57.7,
        "unit": "%",
        "printed": "57.7%",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax-M3.1-Flash (medium)",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "chart image 'Automation-Bench Score vs. Cost per Task (USD)', MiniMax-M3.1-Flash line, point labelled 'medium'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "medium effort; AutomationBench v1.0.6; Claude Code harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/2fe56b1cefe6f716.png",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-5-1792403273121.png"
      },
      {
        "id": "minimax-m3-1-flash:automationbench:default:4",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 59.2,
        "unit": "%",
        "printed": "59.2%",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax-M3.1-Flash (high)",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "chart image 'Automation-Bench Score vs. Cost per Task (USD)', MiniMax-M3.1-Flash line, point labelled 'high'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "high effort; AutomationBench v1.0.6; Claude Code harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/2fe56b1cefe6f716.png",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-5-1792403273121.png"
      },
      {
        "id": "minimax-m3-1-flash:automationbench:default:5",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 61.2,
        "unit": "%",
        "printed": "61.2%",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax-M3.1-Flash (xhigh)",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "chart image 'Automation-Bench Score vs. Cost per Task (USD)', MiniMax-M3.1-Flash line, point labelled 'xhigh'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "xhigh effort; AutomationBench v1.0.6; Claude Code harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/2fe56b1cefe6f716.png",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-5-1792403273121.png"
      },
      {
        "id": "minimax-m3-1-flash:deepswe-1-1:default:2",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 68.1,
        "unit": "%",
        "printed": "68.1%",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax-M3.1-Flash (high)",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "chart image 'DeepSWE v1.1 Score vs. Cost per Task (USD)', MiniMax-M3.1-Flash line, point labelled 'high'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "high effort; mini-swe-agent harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/3f749f378a2e32e4.png",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-4-1792403273121.png"
      },
      {
        "id": "minimax-m3-1-flash:deepswe-1-1:default:3",
        "model": "minimax-m3-1-flash",
        "model_name": "MiniMax M3.1 Flash",
        "model_date": "2026-10-19",
        "event": "https://frontierlog.ai/event/2026-10-19-minimax-m3-1-flash",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 72.1,
        "unit": "%",
        "printed": "72.1%",
        "reported_by": "minimax",
        "run_by": null,
        "label": "MiniMax-M3.1-Flash (xhigh)",
        "source": "https://www.minimax.io/blog/minimax-m31f",
        "source_title": "MiniMax M3.1 Flash: Redefining Agent Performance and Cost",
        "source_date": "2026-10-19",
        "where": "chart image 'DeepSWE v1.1 Score vs. Cost per Task (USD)', MiniMax-M3.1-Flash line, point labelled 'xhigh'",
        "own": true,
        "primary": false,
        "parallel": false,
        "notes": "xhigh effort; mini-swe-agent harness",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-26",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/3f749f378a2e32e4.png",
        "source_image_original": "https://filecdn.minimax.chat/public/m31-flash-en-4-1792403273121.png"
      }
    ]
  }
}