{
  "api_version": "1",
  "updated": "2026-10-29",
  "latest_event": "2026-10-28",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "livecodebench-no-release",
    "name": "LiveCodeBench, no release named",
    "family": "livecodebench",
    "unit": "%",
    "higher_is_better": true,
    "status": "retired",
    "active": false,
    "superseded_by": null,
    "retired": "2026-05-20",
    "benchmark_url": "https://livecodebench.github.io",
    "introduced": "2024-03-12",
    "creator": "UC Berkeley, MIT and Cornell",
    "introduced_source": "https://arxiv.org/abs/2403.07974",
    "settings": [
      {
        "setting": "custom-window",
        "name": "Lab-chosen window",
        "url": "https://frontierlog.ai/benchmark/livecodebench-no-release",
        "results": 29
      },
      {
        "setting": "window-unstated",
        "name": "Window not stated",
        "url": "https://frontierlog.ai/benchmark/livecodebench-no-release/window-unstated",
        "results": 22
      }
    ]
  },
  "total": 22,
  "results": [
    {
      "id": "gemma-2-27b:livecodebench-no-release:window-unstated:1",
      "model": "gemma-2-27b",
      "model_name": "Gemma 2 27B",
      "model_date": "2024-06-27",
      "event": "https://frontierlog.ai/event/2024-06-27-gemma-2",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 20.4,
      "unit": "%",
      "printed": "20.4",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemma 2 27B",
      "source": "https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf",
      "source_title": "Gemma 3 Technical Report",
      "source_date": "2025-03-12",
      "where": "Gemma 3 technical report (PDF), Table 6 (instruction-tuned models), row 'LiveCodeBench', column 'Gemma 2 27B'",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "instruction-tuned; 0-shot; average of 8 samples",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-20",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_capture": "https://frontierlog.ai/captures/f86f02802b4c2394.png"
    },
    {
      "id": "gemma-2-27b:livecodebench-no-release:window-unstated:2",
      "model": "gemma-2-27b",
      "model_name": "Gemma 2 27B",
      "model_date": "2024-06-27",
      "event": "https://frontierlog.ai/event/2024-06-27-gemma-2",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 29.0,
      "unit": "%",
      "printed": "29.0",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemma 2 27B",
      "source": "https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf",
      "source_title": "Gemma 3 Technical Report",
      "source_date": "2025-03-12",
      "where": "Gemma 3 Technical Report, Table 18 (instruction-tuned models, more internal and external benchmarks), page 23, row 'LiveCodeBench', column 'Gemma 2 27B'",
      "own": false,
      "primary": false,
      "parallel": false,
      "notes": "chain of thought; instruction-tuned; 0-shot; average of 8 samples",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "deepseek-v3:livecodebench-no-release:window-unstated:1",
      "model": "deepseek-v3",
      "model_name": "DeepSeek-V3",
      "model_date": "2024-12-26",
      "event": "https://frontierlog.ai/event/2024-12-26-deepseek-v3",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 40.5,
      "unit": "%",
      "printed": "40.5",
      "reported_by": "deepseek",
      "run_by": null,
      "label": "DeepSeek-V3",
      "source": "https://api-docs.deepseek.com/news/news1226/",
      "source_title": "Introducing DeepSeek-V3",
      "source_date": "2024-12-26",
      "where": "benchmark table (image), row 'LiveCodeBench(Pass@1-COT)', column 'DeepSeek-V3'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "chain-of-thought; 8K output limit",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [
        {
          "url": "https://github.com/deepseek-ai/DeepSeek-V3",
          "name": "DeepSeek-V3 card",
          "title": "deepseek-ai/DeepSeek-V3 GitHub repository",
          "lab": "deepseek",
          "date": "2024-12-26",
          "printed": "40.5",
          "where": "README Chat model evaluation table, column \"DeepSeek V3\", row \"LiveCodeBench (Pass@1-COT)\""
        }
      ],
      "source_image": "https://frontierlog.ai/sources/f55e6180f36f8bcf.jpeg",
      "source_image_original": "https://cdn.deepseek.com/api-docs/ds_v3_benchmark_table_en.jpeg"
    },
    {
      "id": "deepseek-v3:livecodebench-no-release:window-unstated:2",
      "model": "deepseek-v3",
      "model_name": "DeepSeek-V3",
      "model_date": "2024-12-26",
      "event": "https://frontierlog.ai/event/2024-12-26-deepseek-v3",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 37.6,
      "unit": "%",
      "printed": "37.6",
      "reported_by": "deepseek",
      "run_by": null,
      "label": "DeepSeek-V3",
      "source": "https://api-docs.deepseek.com/news/news1226/",
      "source_title": "Introducing DeepSeek-V3",
      "source_date": "2024-12-26",
      "where": "benchmark table (image), row 'LiveCodeBench (Pass@1)', column 'DeepSeek-V3'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "without chain-of-thought; 8K output limit",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [
        {
          "url": "https://github.com/deepseek-ai/DeepSeek-V3",
          "name": "DeepSeek-V3 card",
          "title": "deepseek-ai/DeepSeek-V3 GitHub repository",
          "lab": "deepseek",
          "date": "2024-12-26",
          "printed": "37.6",
          "where": "README Chat model evaluation table, column \"DeepSeek V3\", row \"LiveCodeBench (Pass@1)\""
        }
      ],
      "source_image": "https://frontierlog.ai/sources/f55e6180f36f8bcf.jpeg",
      "source_image_original": "https://cdn.deepseek.com/api-docs/ds_v3_benchmark_table_en.jpeg"
    },
    {
      "id": "codestral-25-01:livecodebench-no-release:window-unstated:1",
      "model": "codestral-25-01",
      "model_name": "Codestral 25.01",
      "model_date": "2025-01-13",
      "event": "https://frontierlog.ai/event/2025-01-13-codestral-25-01",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 37.9,
      "unit": "%",
      "printed": "37.9%",
      "reported_by": "mistral",
      "run_by": null,
      "label": "Codestral-2501",
      "source": "https://mistral.ai/news/codestral-2501/",
      "source_title": "Codestral 25.01",
      "source_date": "2025-01-13",
      "where": "'Overview' benchmark table (HTML), Python group, row 'Codestral-2501', column 'LiveCodeBench'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_capture": "https://frontierlog.ai/captures/dee44180c5a2a639.png"
    },
    {
      "id": "gemma-3-27b:livecodebench-no-release:window-unstated:1",
      "model": "gemma-3-27b",
      "model_name": "Gemma 3 27B",
      "model_date": "2025-03-12",
      "event": "https://frontierlog.ai/event/2025-03-12-gemma-3",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 29.7,
      "unit": "%",
      "printed": "29.7",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemma 3 27B",
      "source": "https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf",
      "source_title": "Gemma 3 Technical Report",
      "source_date": "2025-03-12",
      "where": "Table 6 (instruction-tuned models, zero-shot benchmarks), page 6, row 'LiveCodeBench', column 'Gemma 3 27B'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "instruction-tuned; 0-shot; average of 8 samples",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gemma-3-27b:livecodebench-no-release:window-unstated:2",
      "model": "gemma-3-27b",
      "model_name": "Gemma 3 27B",
      "model_date": "2025-03-12",
      "event": "https://frontierlog.ai/event/2025-03-12-gemma-3",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 39.0,
      "unit": "%",
      "printed": "39.0",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemma 3 27B",
      "source": "https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf",
      "source_title": "Gemma 3 Technical Report",
      "source_date": "2025-03-12",
      "where": "Table 18 (instruction-tuned models, more internal and external benchmarks), page 23, row 'LiveCodeBench', column 'Gemma 3 27B'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "chain of thought; instruction-tuned; 0-shot; average of 8 samples",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "llama-nemotron-super-49b-v1:livecodebench-no-release:window-unstated:1",
      "model": "llama-nemotron-super-49b-v1",
      "model_name": "Llama Nemotron Super 49B v1",
      "model_date": "2025-03-18",
      "event": "https://frontierlog.ai/event/2025-03-18-llama-nemotron",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 45.5,
      "unit": "%",
      "printed": "45.5",
      "reported_by": "nvidia",
      "run_by": null,
      "label": "Llama Nemotron Super 49B v1",
      "source": "https://developer.nvidia.com/blog/build-more-accurate-and-efficient-ai-agents-with-the-new-nvidia-llama-nemotron-super-v1-5/",
      "source_title": "Build More Accurate and Efficient AI Agents with the New NVIDIA Llama Nemotron Super v1.5",
      "source_date": "2025-07-29",
      "where": "Figure 2 bar chart (image), value label of the 'Llama Nemotron Super 49B v1' bar (lightest, rightmost in group) in group 'LiveCodeBench'",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-19",
      "corroborated_by": [
        {
          "url": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5/blob/420ba7d28211abf116b8b103ab700d92619daf98/README.md",
          "name": "Llama Nemotron Super v1.5 card",
          "title": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5 model card (revision of 2025-10-15)",
          "lab": "nvidia",
          "date": "2025-07-29",
          "printed": "45.5",
          "where": "accuracy_chart.png bar chart, LiveCodeBench group, 'Llama Nemotron Super 49B v1' bar label"
        },
        {
          "url": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8/blob/04822723e77e036ddf2d24e83c6d469d3b009252/README.md",
          "name": "Llama Nemotron Super v1.5 card",
          "title": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-FP8 model card (revision of 2025-10-15)",
          "lab": "nvidia",
          "date": "2025-07-29",
          "printed": "45.5",
          "where": "accuracy_chart.png bar chart, LiveCodeBench group, 'Llama Nemotron Super 49B v1' bar label"
        },
        {
          "url": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4/blob/f0caaafd5152e07527c7a14e04aa67823107529f/README.md",
          "name": "Llama Nemotron Super v1.5 card",
          "title": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4 model card (revision of 2025-11-27)",
          "lab": "nvidia",
          "date": "2025-07-29",
          "printed": "45.5",
          "where": "accuracy_chart.png bar chart, LiveCodeBench group, 'Llama Nemotron Super 49B v1' bar label"
        }
      ],
      "source_image": "https://frontierlog.ai/sources/d431180dea13f63f.png",
      "source_image_original": "https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image-29.png"
    },
    {
      "id": "deepseek-v3-0324:livecodebench-no-release:window-unstated:1",
      "model": "deepseek-v3-0324",
      "model_name": "DeepSeek-V3-0324",
      "model_date": "2025-03-25",
      "event": "https://frontierlog.ai/event/2025-03-25-deepseek-v3-0324",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 49.2,
      "unit": "%",
      "printed": "49.2",
      "reported_by": "deepseek",
      "run_by": null,
      "label": "DeepSeek-V3-0324",
      "source": "https://api-docs.deepseek.com/news/news250325/",
      "source_title": "DeepSeek-V3-0324 Release",
      "source_date": "2025-03-25",
      "where": "benchmark bar chart (image), group 'LiveCodeBench (Pass@1)', value label on the 'DeepSeek-V3-0324' bar",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [
        {
          "url": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324",
          "name": "DeepSeek-V3-0324 card",
          "title": "deepseek-ai/DeepSeek-V3-0324 model card",
          "lab": "deepseek",
          "date": "2025-03-25",
          "printed": "49.2",
          "where": "card sentence \"LiveCodeBench: 39.2 → 49.2 (+10.0)\""
        }
      ],
      "source_image": "https://frontierlog.ai/sources/0516abeb7983c595.webp",
      "source_image_original": "https://cdn.deepseek.com/api-docs/v3_0324_benchmark.webp"
    },
    {
      "id": "nemotron-nano-9b-v2:livecodebench-no-release:window-unstated:1",
      "model": "nemotron-nano-9b-v2",
      "model_name": "Nemotron Nano 9B v2",
      "model_date": "2025-08-18",
      "event": "https://frontierlog.ai/event/2025-08-18-nemotron-nano-2",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 71.1,
      "unit": "%",
      "printed": "71.1",
      "reported_by": "nvidia",
      "run_by": null,
      "label": "NVIDIA-Nemotron-Nano-9B-v2",
      "source": "https://research.nvidia.com/labs/adlr/NVIDIA-Nemotron-Nano-2/",
      "source_title": "NVIDIA Nemotron Nano 2 and the Nemotron Pretraining Dataset v1",
      "source_date": "2025-08-18",
      "where": "model comparison bar chart (image, 'Measured Accuracy'), value label of the 'NVIDIA-Nemotron-Nano-9B-v2' bar (green) in group 'LiveCodeBench (Coding)'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "reasoning on",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/blob/8bc5eece2eb5514c4bca7f2ec655b91eb554f4c0/README.md",
          "name": "Nemotron Nano 2 card",
          "title": "nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8 model card (revision of 2026-01-08)",
          "lab": "nvidia",
          "date": "2025-08-18",
          "printed": "71.1%",
          "where": "FP8 model card, Benchmark Results (Reasoning On) table, LCB row, NVIDIA-Nemotron-Nano-9B-v2 (BF16) column"
        },
        {
          "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4/blob/8556c9164ddb43fe1f4f4ad730593b3c5e3f7328/README.md",
          "name": "Nemotron Nano 2 card",
          "title": "nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4 model card (revision of 2026-01-08)",
          "lab": "nvidia",
          "date": "2025-08-18",
          "printed": "71.1%",
          "where": "NVFP4 model card, Benchmark Results (Reasoning On) table, LCB row, NVIDIA-Nemotron-Nano-9B-v2 (BF16) column"
        },
        {
          "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2/blob/6533e8de2c68e4536bf7c411d7a3ce5734111476/README.md",
          "name": "Nemotron Nano 2 card",
          "title": "nvidia/NVIDIA-Nemotron-Nano-9B-v2 model card (revision of 2026-03-05)",
          "lab": "nvidia",
          "date": "2025-08-18",
          "printed": "71.1%",
          "where": "Benchmark Results (Reasoning On) table, LCB row, NVIDIA-Nemotron-Nano-9B-v2 column"
        },
        {
          "url": "https://research.nvidia.com/labs/adlr/files/NVIDIA-Nemotron-Nano-2-Technical-Report.pdf",
          "name": "Nemotron Nano 2 card",
          "title": "NVIDIA Nemotron Nano 2 technical report",
          "lab": "nvidia",
          "date": "2025-08-18",
          "printed": "71.1",
          "where": "Figure 1 (Measured Accuracy), LiveCodeBench bar, NVIDIA-Nemotron-Nano-9B-v2 (vector text in PDF)"
        }
      ],
      "source_image": "https://frontierlog.ai/sources/5d46904619c03524.png",
      "source_image_original": "https://research.nvidia.com/labs/adlr/images/nvidia-nemotron-nano-2/nano-2-model-comparison.png"
    },
    {
      "id": "deepseek-v3-1:livecodebench-no-release:window-unstated:1",
      "model": "deepseek-v3-1",
      "model_name": "DeepSeek-V3.1",
      "model_date": "2025-08-21",
      "event": "https://frontierlog.ai/event/2025-08-21-deepseek-v3-1",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 74.8,
      "unit": "%",
      "printed": "74.8%",
      "reported_by": "deepseek",
      "run_by": null,
      "label": "V3.1-Think",
      "source": "https://api-docs.deepseek.com/news/news250821/",
      "source_title": "DeepSeek-V3.1 Release",
      "source_date": "2025-08-21",
      "where": "third image (thinking efficiency bar chart), group 'LiveCodeBench', hatched bar 'V3.1-Think', label above the bar (output tokens, then the score in parentheses)",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "thinking mode; 13,977 output tokens on average",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-19",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/46ed66f55ee72932.webp",
      "source_image_original": "https://cdn.deepseek.com/api-docs/v3.1_benchmark_3.webp"
    },
    {
      "id": "longcat-flash-chat:livecodebench-no-release:window-unstated:1",
      "model": "longcat-flash-chat",
      "model_name": "LongCat-Flash-Chat",
      "model_date": "2025-09-01",
      "event": "https://frontierlog.ai/event/2025-09-01-longcat-flash-chat",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 48.02,
      "unit": "%",
      "printed": "48.02",
      "reported_by": "meituan",
      "run_by": null,
      "label": "LongCat-Flash",
      "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Chat",
      "source_title": "LongCat-Flash-Chat model card (Hugging Face)",
      "source_date": "2025-09-01",
      "where": "model card, Evaluation Results table, row 'LiveCodeBench (pass@1)', column 'LongCat-Flash'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "non-thinking",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://huggingface.co/meituan-longcat/LongCat-Flash-Omni",
          "name": "LongCat-Flash-Omni card",
          "title": "LongCat-Flash-Omni model card (Hugging Face)",
          "lab": "meituan",
          "date": "2025-11-03",
          "printed": "48.02",
          "where": "LongCat-Flash-Omni HF card, Text table, LiveCodeBench (pass@1) row, 'LongCat-Flash' column"
        },
        {
          "url": "https://github.com/meituan-longcat/LongCat-Flash-Chat",
          "name": "LongCat-Flash-Chat card",
          "title": "LongCat-Flash-Chat GitHub repository",
          "lab": "meituan",
          "date": "2025-09-01",
          "printed": "48.02",
          "where": "GitHub README, evaluation table, LiveCodeBench (pass@1) row, LongCat-Flash column"
        },
        {
          "url": "https://github.com/meituan-longcat/LongCat-Flash-Chat/blob/main/tech_report.pdf",
          "name": "LongCat-Flash-Chat card",
          "title": "LongCat-Flash Technical Report",
          "lab": "meituan",
          "date": "2025-09-01",
          "printed": "48.02",
          "where": "LongCat-Flash Technical Report (PDF in the lab's GitHub repo), chat-model evaluation table, LiveCodeBench (pass@1) row, LongCat-Flash column"
        },
        {
          "url": "https://github.com/meituan-longcat/LongCat-Flash-Omni",
          "name": "LongCat-Flash-Omni card",
          "title": "LongCat-Flash-Omni GitHub repository",
          "lab": "meituan",
          "date": "2025-11-03",
          "printed": "48.02",
          "where": "LongCat-Flash-Omni GitHub README, Text table, LiveCodeBench (pass@1) row, 'LongCat-Flash' column"
        },
        {
          "url": "https://github.com/meituan-longcat/LongCat-Flash-Omni/blob/main/tech_report.pdf",
          "name": "LongCat-Flash-Omni card",
          "title": "LongCat-Flash-Omni Technical Report",
          "lab": "meituan",
          "date": "2025-11-03",
          "printed": "48.02",
          "where": "LongCat-Flash-Omni Technical Report, Table 13 (frontier chat/instruct models), LiveCodeBench (pass@1) row, 'LongCat-Flash' column"
        }
      ],
      "source_capture": "https://frontierlog.ai/captures/b4e44a3a773f84f7.png"
    },
    {
      "id": "minimax-m2:livecodebench-no-release:window-unstated:1",
      "model": "minimax-m2",
      "model_name": "MiniMax M2",
      "model_date": "2025-10-27",
      "event": "https://frontierlog.ai/event/2025-10-27-minimax-m2",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 83.0,
      "unit": "%",
      "printed": "83.0",
      "reported_by": "minimax",
      "run_by": null,
      "label": "MiniMax-M2",
      "source": "https://www.minimax.io/news/minimax-m21",
      "source_title": "MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks",
      "source_date": "2025-12-23",
      "where": "later report: MiniMax-M2.1 post, 'Benchmarks' section, last (long-horizon tool use and intelligence) table image, row 'LCB', column 'MiniMax-M2'",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "internal run following Artificial Analysis Intelligence Index methods",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1",
          "name": "MiniMax M2.1 card",
          "title": "MiniMaxAI/MiniMax-M2.1 model card",
          "lab": "minimax",
          "date": "2025-12-23",
          "printed": "83.0",
          "where": "M2.1 card AA-method table, column \"MiniMax-M2\", row \"LCB\""
        },
        {
          "url": "https://github.com/MiniMax-AI/MiniMax-M2.1",
          "name": "MiniMax M2.1 card",
          "title": "MiniMax-M2.1 GitHub repository",
          "lab": "minimax",
          "date": "2025-12-23",
          "printed": "83.0",
          "where": "M2.1 README AA-method table, column \"MiniMax-M2\", row \"LCB\""
        }
      ],
      "source_image": "https://frontierlog.ai/sources/78a04f05b9d1589b.png",
      "source_image_original": "https://file.cdn.minimax.io/public/6aaadb26-4395-46ba-9ebe-f858f3bc0c6b.png"
    },
    {
      "id": "longcat-flash-omni:livecodebench-no-release:window-unstated:1",
      "model": "longcat-flash-omni",
      "model_name": "LongCat-Flash-Omni",
      "model_date": "2025-11-03",
      "event": "https://frontierlog.ai/event/2025-11-03-longcat-flash-omni",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 52.64,
      "unit": "%",
      "printed": "52.64",
      "reported_by": "meituan",
      "run_by": null,
      "label": "LongCat-Flash-Omni Instruct",
      "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Omni",
      "source_title": "LongCat-Flash-Omni model card (Hugging Face)",
      "source_date": "2025-11-03",
      "where": "model card, Text benchmark table (collapsed 'Text' section), row 'LiveCodeBench (pass@1)', column 'LongCat-Flash-Omni Instruct'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://github.com/meituan-longcat/LongCat-Flash-Omni",
          "name": "LongCat-Flash-Omni card",
          "title": "LongCat-Flash-Omni GitHub repository",
          "lab": "meituan",
          "date": "2025-11-03",
          "printed": "52.64",
          "where": "GitHub README, Text table, LiveCodeBench (pass@1) row, LongCat-Flash-Omni Instruct column"
        },
        {
          "url": "https://github.com/meituan-longcat/LongCat-Flash-Omni/blob/main/tech_report.pdf",
          "name": "LongCat-Flash-Omni card",
          "title": "LongCat-Flash-Omni Technical Report",
          "lab": "meituan",
          "date": "2025-11-03",
          "printed": "52.64",
          "where": "Technical Report (PDF in GitHub repo), Table 13, LiveCodeBench (pass@1) row, LongCat-Flash-Omni Instruct column"
        }
      ],
      "source_capture": "https://frontierlog.ai/captures/afb0fa5cde611f0c.png"
    },
    {
      "id": "gigachat-3-lightning:livecodebench-no-release:window-unstated:1",
      "model": "gigachat-3-lightning",
      "model_name": "GigaChat 3 Lightning",
      "model_date": "2025-11-21",
      "event": "https://frontierlog.ai/event/2025-11-21-gigachat-3-ultra-preview",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 20.31,
      "unit": "%",
      "printed": "0,2031",
      "reported_by": "sber",
      "run_by": null,
      "label": "GigaChat-Lightning-sft",
      "source": "https://habr.com/ru/companies/sberdevices/articles/968904/",
      "source_title": "GigaChat 3 Ultra Preview — тяжёлый open source",
      "source_date": "2025-11-21",
      "where": "alignment metrics table (HTML, under 'Alignment-метрики'), row 'LiveCodeBench_ZERO_SHOT', column 'GigaChat-Lightning-sft'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "0-shot",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_capture": "https://frontierlog.ai/captures/bde5428c2608d17f.png"
    },
    {
      "id": "mistral-large-3:livecodebench-no-release:window-unstated:1",
      "model": "mistral-large-3",
      "model_name": "Mistral Large 3 675B",
      "model_date": "2025-12-02",
      "event": "https://frontierlog.ai/event/2025-12-02-mistral-3",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 34.4,
      "unit": "%",
      "printed": "34.4",
      "reported_by": "mistral",
      "run_by": null,
      "label": "Mistral Large 3 (675B)",
      "source": "https://mistral.ai/news/mistral-3/",
      "source_title": "Introducing Mistral 3",
      "source_date": "2025-12-02",
      "where": "'Base Model Benchmark Comparison' bar chart image, group 'LiveCodeBench (no CoT)', bar 'Mistral Large 3 (675B)', value label",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "base model, before instruction tuning; no chain of thought",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-20",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/b74e86a313e7eaf2.webp",
      "source_image_original": "https://mistral.ai/_astro/98aeee04-e1c3-43b7-b90e-c51da84d5e56_19WeLG.webp"
    },
    {
      "id": "minimax-m2-1:livecodebench-no-release:window-unstated:1",
      "model": "minimax-m2-1",
      "model_name": "MiniMax M2.1",
      "model_date": "2025-12-23",
      "event": "https://frontierlog.ai/event/2025-12-23-minimax-m2-1",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 78.0,
      "unit": "%",
      "printed": "78.0",
      "reported_by": "minimax",
      "run_by": null,
      "label": "MiniMax-M2.1",
      "source": "https://www.minimax.io/news/minimax-m21",
      "source_title": "MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks",
      "source_date": "2025-12-23",
      "where": "'Benchmarks' section, last (long-horizon tool use and intelligence) table image, row 'LCB', column 'MiniMax-M2.1'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "internal run following Artificial Analysis Intelligence Index methods",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/78a04f05b9d1589b.png",
      "source_image_original": "https://file.cdn.minimax.io/public/6aaadb26-4395-46ba-9ebe-f858f3bc0c6b.png"
    },
    {
      "id": "minimax-m2-1:livecodebench-no-release:window-unstated:2",
      "model": "minimax-m2-1",
      "model_name": "MiniMax M2.1",
      "model_date": "2025-12-23",
      "event": "https://frontierlog.ai/event/2025-12-23-minimax-m2-1",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 81.0,
      "unit": "%",
      "printed": "81.0",
      "reported_by": "minimax",
      "run_by": null,
      "label": "MiniMax-M2.1",
      "source": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1",
      "source_title": "MiniMaxAI/MiniMax-M2.1 model card",
      "source_date": "2025-12-23",
      "where": "model card, long-horizon tool use and intelligence table, row 'LCB', column 'MiniMax-M2.1'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "internal run following Artificial Analysis Intelligence Index methods",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://github.com/MiniMax-AI/MiniMax-M2.1",
          "name": "MiniMax M2.1 card",
          "title": "MiniMax-M2.1 GitHub repository",
          "lab": "minimax",
          "date": "2025-12-23",
          "printed": "81.0",
          "where": "README AA-method table, column \"MiniMax-M2.1\", row \"LCB\""
        }
      ],
      "source_capture": "https://frontierlog.ai/captures/e2ae654583722dcb.png"
    },
    {
      "id": "mistral-small-4:livecodebench-no-release:window-unstated:1",
      "model": "mistral-small-4",
      "model_name": "Mistral Small 4 119B",
      "model_date": "2026-03-16",
      "event": "https://frontierlog.ai/event/2026-03-16-mistral-small-4",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 63.6,
      "unit": "%",
      "printed": "63.6",
      "reported_by": "mistral",
      "run_by": null,
      "label": "Mistral Small 4 - High",
      "source": "https://mistral.ai/news/mistral-small-4/",
      "source_title": "Introducing Mistral Small 4",
      "source_date": "2026-03-16",
      "where": "chart image 'Performance comparison across internal models' (second), group 'LiveCodeBench', bar 'Mistral Small 4 - High', value label",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "high reasoning effort",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/6a20cec3b0654df9.webp",
      "source_image_original": "https://mistral.ai/_astro/f6b89244-752a-45ce-8eed-166a58680399_138EpE.webp"
    },
    {
      "id": "deepseek-v4-flash:livecodebench-no-release:window-unstated:1",
      "model": "deepseek-v4-flash",
      "model_name": "DeepSeek-V4-Flash",
      "model_date": "2026-04-24",
      "event": "https://frontierlog.ai/event/2026-04-24-deepseek-v4-preview",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 91.6,
      "unit": "%",
      "printed": "91.6",
      "reported_by": "deepseek",
      "run_by": null,
      "label": "DS-V4-Flash Max",
      "source": "https://api-docs.deepseek.com/news/news260424/",
      "source_title": "DeepSeek V4 Preview Release",
      "source_date": "2026-04-24",
      "where": "benchmark table (second image), row 'LiveCodeBench (Pass@1)', column 'DS-V4-Flash Max'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "max reasoning effort",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro",
          "name": "DeepSeek V4 Preview card",
          "title": "DeepSeek-V4-Pro model card",
          "lab": "deepseek",
          "date": "2026-04-24",
          "printed": "91.6",
          "where": "card instruct table (non-think/high/max), column \"V4-Flash Max\", row \"LiveCodeBench (Pass@1)\""
        }
      ],
      "source_image": "https://frontierlog.ai/sources/9226203de8e24b33.png",
      "source_image_original": "https://api-docs.deepseek.com/img/v4-benchmark-2.png"
    },
    {
      "id": "deepseek-v4-pro:livecodebench-no-release:window-unstated:1",
      "model": "deepseek-v4-pro",
      "model_name": "DeepSeek-V4-Pro",
      "model_date": "2026-04-24",
      "event": "https://frontierlog.ai/event/2026-04-24-deepseek-v4-preview",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 93.5,
      "unit": "%",
      "printed": "93.5",
      "reported_by": "deepseek",
      "run_by": null,
      "label": "DS-V4-Pro Max",
      "source": "https://api-docs.deepseek.com/news/news260424/",
      "source_title": "DeepSeek V4 Preview Release",
      "source_date": "2026-04-24",
      "where": "benchmark table image, row 'LiveCodeBench (Pass@1)', column 'DS-V4-Pro Max'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "max reasoning effort",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-18",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/9226203de8e24b33.png",
      "source_image_original": "https://api-docs.deepseek.com/img/v4-benchmark-2.png"
    },
    {
      "id": "qwen3-7-max:livecodebench-no-release:window-unstated:1",
      "model": "qwen3-7-max",
      "model_name": "Qwen3.7-Max",
      "model_date": "2026-05-20",
      "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
      "benchmark": "livecodebench-no-release",
      "benchmark_name": "LiveCodeBench, no release named",
      "setting": "window-unstated",
      "setting_name": "Window not stated",
      "score": 91.6,
      "unit": "%",
      "printed": "91.6",
      "reported_by": "alibaba",
      "run_by": null,
      "label": "Qwen3.7-Max",
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "source_title": "Qwen3.7: The Agent Frontier",
      "source_date": "2026-05-20",
      "where": "'Performance' table, row 'LiveCodeBench', column 'Qwen3.7-Max'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-19",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
    }
  ]
}