{
  "models": [
    {
      "name": "Claude Opus 4.8",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 47.06,
      "score_hack_control": 47.06,
      "date": "2026-07-12",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "Claude Sonnet 5",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 37.25,
      "score_hack_control": 36.27,
      "date": "2026-07-12",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "Claude Opus 4.7",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 44.12,
      "score_hack_control": 42.16,
      "date": "2026-04-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "Claude Opus 4.6",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 41.18,
      "score_hack_control": 37.25,
      "date": "2026-04-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "GPT 5.5",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 40.2,
      "score_hack_control": 37.25,
      "date": "2026-04-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "GPT 5.4",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 31.37,
      "score_hack_control": 30.39,
      "date": "2026-03-10",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "GPT 5.4",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 25.49,
      "score_hack_control": 22.55,
      "date": "2026-03-10",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "Gemini 3.1 Pro",
      "model_org": "Google",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 22.55,
      "score_hack_control": 21.57,
      "date": "2026-03-09",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Claude Opus 4.6",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 33.33,
      "score_hack_control": 30.39,
      "date": "2026-02-11",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Gemini 3 Flash",
      "model_org": "Google",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 9.8,
      "score_hack_control": 7.84,
      "date": "2025-12-19",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "GPT 5.2",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 27.45,
      "score_hack_control": 26.47,
      "date": "2025-12-18",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "GPT 5.1",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 13.73,
      "score_hack_control": 12.75,
      "date": "2025-12-18",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "Claude Opus 4.5",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 26.47,
      "score_hack_control": 24.5,
      "date": "2025-11-28",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Gemini 3 Pro",
      "model_org": "Google",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 18.63,
      "score_hack_control": 17.65,
      "date": "2025-11-28",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Gemini 2.5 Pro",
      "model_org": "Google",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 3.92,
      "score_hack_control": 0.0,
      "date": "2025-10-10",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Claude Sonnet 4.5",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 14.71,
      "score_hack_control": 12.74,
      "date": "2025-10-10",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Qwen3 Coder",
      "model_org": "Qwen",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 4.9,
      "score_hack_control": 3.92,
      "date": "2025-09-02",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "GLM 4.5 Air",
      "model_org": "z.ai",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 2.94,
      "score_hack_control": 0.98,
      "date": "2025-08-26",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Kimi K2 Instruct",
      "model_org": "moonshotai",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 4.9,
      "score_hack_control": 1.96,
      "date": "2025-08-26",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "GPT 5",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 6.86,
      "score_hack_control": 5.88,
      "date": "2025-08-10",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "Claude Opus 4",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 6.86,
      "score_hack_control": 4.9,
      "date": "2025-08-10",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "O3",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 8.82,
      "score_hack_control": 3.92,
      "date": "2025-06-09",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "Claude Sonnet 4",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 4.9,
      "score_hack_control": 4.9,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Claude Sonnet 3.7",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 3.8,
      "score_hack_control": 3.8,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Claude Sonnet 3.5 V2",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 4.6,
      "score_hack_control": 4.6,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Claude Sonnet 3.5 V2",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@10",
      "score": 15.7,
      "score_hack_control": 15.7,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "O4 Mini",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 3.6,
      "score_hack_control": 3.6,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "O4 Mini",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@10",
      "score": 12.7,
      "score_hack_control": 12.7,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "O3 Mini",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 1.3,
      "score_hack_control": 1.3,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "high"
    },
    {
      "name": "GPT 4o",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 0.0,
      "score_hack_control": 0.0,
      "date": "2025-05-30",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO"
    },
    {
      "name": "Claude Fable 5.1",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 88.24,
      "score_hack_control": 87.25,
      "date": "2026-09-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "GPT-6 Astra",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 79.41,
      "score_hack_control": 77.45,
      "date": "2026-09-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "Claude Fable 5",
      "model_org": "Anthropic",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 78.43,
      "score_hack_control": 76.47,
      "date": "2026-09-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    },
    {
      "name": "GPT-5.6 Sol",
      "model_org": "OpenAI",
      "scaffold": "OpenHands",
      "setting": "Opt@1",
      "score": 76.47,
      "score_hack_control": 70.59,
      "date": "2026-09-27",
      "submission_org_logo": "",
      "submission_org_url": "https://gso-bench.github.io/",
      "submission_org_name": "GSO",
      "reasoning_effort": "xhigh"
    }
  ],
  "metadata": {
    "last_updated": "2026-09-27",
    "total_tasks": 102
  }
}
