{
  "api_version": "1",
  "updated": "2026-10-29",
  "latest_event": "2026-10-28",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "livecodebench-v5",
    "name": "LiveCodeBench v5",
    "family": "livecodebench",
    "unit": "%",
    "higher_is_better": true,
    "status": "superseded",
    "active": false,
    "superseded_by": "livecodebench-v6",
    "retired": null,
    "benchmark_url": "https://livecodebench.github.io",
    "introduced": "2025-01-14",
    "creator": "UC Berkeley, MIT and Cornell",
    "introduced_source": "https://huggingface.co/datasets/livecodebench/code_generation_lite/commit/0687ab61843a90a0cc864a2b67db729861cd0ae5",
    "settings": [
      {
        "setting": "default",
        "name": "",
        "url": "https://frontierlog.ai/benchmark/livecodebench-v5",
        "results": 12
      }
    ]
  },
  "total": 12,
  "results": [
    {
      "id": "gemini-2-0-flash:livecodebench-v5:default:1",
      "model": "gemini-2-0-flash",
      "model_name": "Gemini 2.0 Flash",
      "model_date": "2024-12-11",
      "event": "https://frontierlog.ai/event/2024-12-11-gemini-2-0-flash",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 34.5,
      "unit": "%",
      "printed": "34.5%",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemini 2.0 Flash GA",
      "source": "https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-model-updates-february-2025/",
      "source_title": "Gemini 2.0 is now available to everyone",
      "source_date": "2025-02-05",
      "where": "benchmark table (image), row 'Code, LiveCodeBench (v5)', column 'Gemini 2.0 Flash GA'",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "generally available version; problems from 10/01/2024 to 02/01/2025",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://blog.google/products-and-platforms/products/gemini/gemini-2-5-flash-preview/",
          "name": "Gemini 2.5 Flash",
          "title": "Developers can now start building with Gemini 2.5 Flash.",
          "lab": "google",
          "date": "2025-04-17",
          "printed": "34.5%",
          "where": "Benchmark table image, row LiveCodeBench v5 single attempt (pass@1), column Gemini 2.0 Flash Non-thinking; footer: LiveCodeBench 10/1/2024-2/1/2025"
        },
        {
          "url": "https://developers.googleblog.com/en/start-building-with-gemini-25-flash/",
          "name": "Gemini 2.5 Flash card",
          "title": "Start building with Gemini 2.5 Flash",
          "lab": "google",
          "date": "2025-04-17",
          "printed": "34.5%",
          "where": "Benchmark table image, row LiveCodeBench v5 single attempt (pass@1), column Gemini 2.0 Flash Non-thinking; footer: LiveCodeBench 10/1/2024-2/1/2025"
        },
        {
          "url": "https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf",
          "name": "Gemma 3 card",
          "title": "Gemma 3 Technical Report",
          "lab": "google",
          "date": "2025-03-12",
          "printed": "34.5",
          "where": "Table 6, row LiveCodeBench, column Gemini 2.0 Flash (problem window not stated)"
        }
      ],
      "source_image": "https://frontierlog.ai/sources/e62f7246ad12052e.gif",
      "source_image_original": "https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini_benchmarks_cropped_light1x.gif"
    },
    {
      "id": "gemini-2-0-flash-lite:livecodebench-v5:default:1",
      "model": "gemini-2-0-flash-lite",
      "model_name": "Gemini 2.0 Flash-Lite",
      "model_date": "2025-02-05",
      "event": "https://frontierlog.ai/event/2025-02-05-gemini-2-0-flash-flash-lite-and-pro",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 28.9,
      "unit": "%",
      "printed": "28.9%",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemini 2.0 Flash-Lite Public preview",
      "source": "https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-model-updates-february-2025/",
      "source_title": "Gemini 2.0 is now available to everyone",
      "source_date": "2025-02-05",
      "where": "benchmark table (image), row 'Code, LiveCodeBench (v5)', column 'Gemini 2.0 Flash-Lite Public preview'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "public preview; problems from 10/01/2024 to 02/01/2025",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/e62f7246ad12052e.gif",
      "source_image_original": "https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini_benchmarks_cropped_light1x.gif"
    },
    {
      "id": "gemini-2-0-pro:livecodebench-v5:default:1",
      "model": "gemini-2-0-pro",
      "model_name": "Gemini 2.0 Pro",
      "model_date": "2025-02-05",
      "event": "https://frontierlog.ai/event/2025-02-05-gemini-2-0-flash-flash-lite-and-pro",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 36.0,
      "unit": "%",
      "printed": "36.0%",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemini 2.0 Pro Experimental",
      "source": "https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-model-updates-february-2025/",
      "source_title": "Gemini 2.0 is now available to everyone",
      "source_date": "2025-02-05",
      "where": "benchmark table (image), row 'Code, LiveCodeBench (v5)', column 'Gemini 2.0 Pro Experimental'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "experimental version; problems from 10/01/2024 to 02/01/2025",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://storage.googleapis.com/deepmind-media/gemma/Gemma3Report.pdf",
          "name": "Gemma 3 card",
          "title": "Gemma 3 Technical Report",
          "lab": "google",
          "date": "2025-03-12",
          "printed": "36.0",
          "where": "Table 6, row LiveCodeBench, column Gemini 2.0 Pro (problem window not stated; version not labelled)"
        }
      ],
      "source_image": "https://frontierlog.ai/sources/e62f7246ad12052e.gif",
      "source_image_original": "https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini_benchmarks_cropped_light1x.gif"
    },
    {
      "id": "gemini-2-5-pro:livecodebench-v5:default:1",
      "model": "gemini-2-5-pro",
      "model_name": "Gemini 2.5 Pro",
      "model_date": "2025-03-25",
      "event": "https://frontierlog.ai/event/2025-03-25-gemini-2-5-pro",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 70.4,
      "unit": "%",
      "printed": "70.4%",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemini 2.5 Pro Experimental (03-25)",
      "source": "https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-model-thinking-updates-march-2025/",
      "source_title": "Gemini 2.5: Our most intelligent AI model",
      "source_date": "2025-03-25",
      "where": "benchmark table (image), row 'Code generation, LiveCodeBench v5, single attempt (pass@1)', column 'Gemini 2.5 Pro Experimental (03-25)'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "single attempt; pass@1; problems from 10/1/2024 to 2/1/2025",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-29",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_image": "https://frontierlog.ai/sources/a8f4323681d1a15d.gif",
      "source_image_original": "https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini_benchmarks_cropped_light2x_1PPmDuP.gif"
    },
    {
      "id": "gemini-2-5-flash:livecodebench-v5:default:1",
      "model": "gemini-2-5-flash",
      "model_name": "Gemini 2.5 Flash",
      "model_date": "2025-04-17",
      "event": "https://frontierlog.ai/event/2025-04-17-gemini-2-5-flash",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 63.5,
      "unit": "%",
      "printed": "63.5%",
      "reported_by": "google",
      "run_by": null,
      "label": "Gemini 2.5 Flash Preview (04-17) Thinking",
      "source": "https://blog.google/products-and-platforms/products/gemini/gemini-2-5-flash-preview/",
      "source_title": "Developers can now start building with Gemini 2.5 Flash.",
      "source_date": "2025-04-17",
      "where": "benchmark table (image), row 'Code generation, LiveCodeBench v5, single attempt (pass@1)', column 'Gemini 2.5 Flash Preview (04-17) Thinking'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "thinking; single attempt; pass@1; problems from 10/1/2024 to 2/1/2025",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-28",
      "corroborated_by": [
        {
          "url": "https://developers.googleblog.com/en/start-building-with-gemini-25-flash/",
          "name": "Gemini 2.5 Flash card",
          "title": "Start building with Gemini 2.5 Flash",
          "lab": "google",
          "date": "2025-04-17",
          "printed": "63.5%",
          "where": "Benchmark table image, row Code generation LiveCodeBench v5 single attempt (pass@1), column Gemini 2.5 Flash Preview (04-17) Thinking; footer window 10/1/2024-2/1/2025"
        }
      ],
      "source_image": "https://frontierlog.ai/sources/8cd52ccb5d3627c2.gif",
      "source_image_original": "https://storage.googleapis.com/gweb-uniblog-publish-prod/original_images/gemini_2-5_flash_benchmarks_apr.google.gif"
    },
    {
      "id": "qwen3-235b-a22b:livecodebench-v5:default:1",
      "model": "qwen3-235b-a22b",
      "model_name": "Qwen3-235B-A22B",
      "model_date": "2025-04-29",
      "event": "https://frontierlog.ai/event/2025-04-29-qwen3",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 70.7,
      "unit": "%",
      "printed": "70.7",
      "reported_by": "alibaba",
      "run_by": null,
      "label": "Qwen3-235B-A22B",
      "source": "https://qwen.ai/blog?id=qwen3",
      "source_title": "Qwen3: Think Deeper, Act Faster",
      "source_date": "2025-04-29",
      "where": "first table image (flagship comparison), row 'LiveCodeBench v5, 2024.10-2025.02', column 'Qwen3-235B-A22B'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "problems from Oct 2024 to Feb 2025",
      "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/85992a4471a0222e.jpg",
      "source_image_original": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3/qwen3-235a22.jpg"
    },
    {
      "id": "mistral-medium-3:livecodebench-v5:default:1",
      "model": "mistral-medium-3",
      "model_name": "Mistral Medium 3",
      "model_date": "2025-05-07",
      "event": "https://frontierlog.ai/event/2025-05-07-mistral-medium-3",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 29.1,
      "unit": "%",
      "printed": "29.1%",
      "reported_by": "mistral",
      "run_by": null,
      "label": "Mistral-Medium 3",
      "source": "https://mistral.ai/news/magistral/",
      "source_title": "Magistral",
      "source_date": "2025-06-10",
      "where": "later report: Magistral post, bar chart image ('Plot Magistral'), group 'LiveCodeBench (v5)', first bar (legend 'Mistral-Medium 3'), value label",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "",
      "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/84531142934214ea.webp",
      "source_image_original": "https://mistral.ai/_astro/d73ee721-ea92-46f5-af77-79674fdb4163_Z1B7kp2.webp"
    },
    {
      "id": "magistral-medium:livecodebench-v5:default:1",
      "model": "magistral-medium",
      "model_name": "Magistral Medium",
      "model_date": "2025-06-10",
      "event": "https://frontierlog.ai/event/2025-06-10-magistral",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 59.4,
      "unit": "%",
      "printed": "59.4%",
      "reported_by": "mistral",
      "run_by": null,
      "label": "Magistral-Medium",
      "source": "https://mistral.ai/news/magistral/",
      "source_title": "Magistral",
      "source_date": "2025-06-10",
      "where": "bar chart image ('Plot Magistral'), group 'LiveCodeBench (v5)', second bar (legend 'Magistral-Medium'), value label",
      "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://huggingface.co/mistralai/Magistral-Small-2506",
          "name": "Magistral card",
          "title": "mistralai/Magistral-Small-2506 model card",
          "lab": "mistral",
          "date": "2025-06-10",
          "printed": "59.36%",
          "where": "Benchmark Results table, row 'Magistral Medium', column 'Livecodebench (v5)'"
        }
      ],
      "source_image": "https://frontierlog.ai/sources/84531142934214ea.webp",
      "source_image_original": "https://mistral.ai/_astro/d73ee721-ea92-46f5-af77-79674fdb4163_Z1B7kp2.webp"
    },
    {
      "id": "magistral-small:livecodebench-v5:default:1",
      "model": "magistral-small",
      "model_name": "Magistral Small",
      "model_date": "2025-06-10",
      "event": "https://frontierlog.ai/event/2025-06-10-magistral",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 55.84,
      "unit": "%",
      "printed": "55.84%",
      "reported_by": "mistral",
      "run_by": null,
      "label": "Magistral Small",
      "source": "https://huggingface.co/mistralai/Magistral-Small-2506",
      "source_title": "mistralai/Magistral-Small-2506 model card",
      "source_date": "2025-06-10",
      "where": "Hugging Face model card, 'Benchmark Results' table, row 'Magistral Small', column 'Livecodebench (v5)'",
      "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/a894d95d2768d75b.png"
    },
    {
      "id": "nemotron-3-nano-30b-a3b:livecodebench-v5:default:1",
      "model": "nemotron-3-nano-30b-a3b",
      "model_name": "Nemotron 3 Nano 30B-A3B",
      "model_date": "2025-12-15",
      "event": "https://frontierlog.ai/event/2025-12-15-nemotron-3",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 72.1,
      "unit": "%",
      "printed": "72.1",
      "reported_by": "nvidia",
      "run_by": null,
      "label": "BF16",
      "source": "https://research.nvidia.com/labs/nemotron/files/NVFP4-QAD-Report.pdf",
      "source_title": "Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery",
      "source_date": "2026-03-05",
      "where": "NVFP4 QAD report, Table 3(a) (Nemotron 3 Nano), row 'BF16', column 'LiveCodeBench-v5'",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "BF16 baseline of an NVFP4 quantization study",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "nemotron-3-super-120b-a12b:livecodebench-v5:default:1",
      "model": "nemotron-3-super-120b-a12b",
      "model_name": "Nemotron 3 Super 120B-A12B",
      "model_date": "2026-03-11",
      "event": "https://frontierlog.ai/event/2026-03-11-nemotron-3-super",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 81.19,
      "unit": "%",
      "printed": "81.19",
      "reported_by": "nvidia",
      "run_by": null,
      "label": "Nemotron-3-Super",
      "source": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8/blob/1408abd63ba6ba1c37a78b94d332dac35da45370/README.md",
      "source_title": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 model card (launch-day revision)",
      "source_date": "2026-03-11",
      "where": "benchmark table under the accuracy chart, row 'LiveCodeBench (v5 2024-07...2024-12)', column 'Nemotron-3-Super'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "problems from Jul to Dec 2024",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-19",
      "corroborated_by": [
        {
          "url": "https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Super-Technical-Report.pdf",
          "name": "Nemotron 3 Super card",
          "title": "Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning",
          "lab": "nvidia",
          "date": "2026-03-11",
          "printed": "81.19",
          "where": "Table 5, LiveCodeBench (v5 2024-07↔2024-12) row, N-3-Super column"
        },
        {
          "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16/blob/2dc98e2afe4face0e4ce40972a915c45368bd34a/README.md",
          "name": "Nemotron 3 Super card",
          "title": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 model card (revision of 2026-08-25)",
          "lab": "nvidia",
          "date": "2026-03-11",
          "printed": "81.19",
          "where": "Benchmarks table, 'Nemotron 3 Super' column, LiveCodeBench (v5 2024-07↔2024-12) row"
        },
        {
          "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4/blob/ff433f5493e25d631c9f12b5d55c674229923d02/README.md",
          "name": "Nemotron 3 Super card",
          "title": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 model card (revision of 2026-08-24)",
          "lab": "nvidia",
          "date": "2026-03-11",
          "printed": "81.19",
          "where": "accuracy table, 'Nemotron-3-Super' (BF16) column, LiveCodeBench (v5 2024-07↔2024-12) row"
        }
      ],
      "source_capture": "https://frontierlog.ai/captures/0a1e755f970190a7.png"
    },
    {
      "id": "nemotron-3-nano-omni-30b-a3b:livecodebench-v5:default:1",
      "model": "nemotron-3-nano-omni-30b-a3b",
      "model_name": "Nemotron 3 Nano Omni 30B-A3B",
      "model_date": "2026-04-28",
      "event": "https://frontierlog.ai/event/2026-04-28-nemotron-3-nano-omni",
      "benchmark": "livecodebench-v5",
      "benchmark_name": "LiveCodeBench v5",
      "setting": "default",
      "setting_name": "",
      "score": 63.2,
      "unit": "%",
      "printed": "63.2",
      "reported_by": "nvidia",
      "run_by": null,
      "label": "Nemotron 3 Nano Omni",
      "source": "https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Omni-report.pdf",
      "source_title": "Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence",
      "source_date": "2026-04-28",
      "where": "technical report, Table 10 (text-only benchmarks), row 'LiveCodeBench', column 'Nemotron 3 Nano Omni'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "problems from Jul 2024 to May 2025; single run",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    }
  ]
}