{
  "license": "CC-BY-4.0",
  "sources": [
    {
      "id": "epoch",
      "name": "Epoch AI",
      "url": "https://epoch.ai/benchmarks",
      "license": "CC-BY-4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution_text": "Epoch AI Benchmarking Hub, CC BY 4.0"
    }
  ],
  "records": [
    {
      "model_name": "Qwen2.5-Max",
      "model_version": "Qwen2.5-Max",
      "benchmark_id": "gpqa-diamond",
      "value": 56.1,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-04-01",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-01-25",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3-235B-A22B",
      "model_version": "Qwen3-235B-A22B",
      "benchmark_id": "gpqa-diamond",
      "value": 70.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-06-03",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-04-29",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3-235B-A22B (Jul 2025)",
      "model_version": "Qwen3-235B-A22B (Jul 2025)",
      "benchmark_id": "gpqa-diamond",
      "value": 80.1,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-12-11",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-07-25",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3-Max",
      "model_version": "Qwen3-Max",
      "benchmark_id": "gpqa-diamond",
      "value": 72.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-10-06",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-09-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3.5 397B-A17B",
      "model_version": "Qwen3.5 397B-A17B",
      "benchmark_id": "gpqa-diamond",
      "value": 86.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-02-13",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen 3.6 Max (Preview)",
      "model_version": "Qwen 3.6 Max (Preview)",
      "benchmark_id": "gpqa-diamond",
      "value": 87.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-04-20",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3.7-Max",
      "model_version": "Qwen3.7-Max",
      "benchmark_id": "gpqa-diamond",
      "value": 90.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-05-19",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen 3.8 Max",
      "model_version": "Qwen 3.8 Max",
      "benchmark_id": "gpqa-diamond",
      "value": 92.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-04",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-08-02",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3.8 Max (0902)",
      "model_version": "Qwen3.8 Max (0902)",
      "benchmark_id": "gpqa-diamond",
      "value": 92.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-09-02",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-09-01",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-R1",
      "model_version": "DeepSeek-R1",
      "benchmark_id": "gpqa-diamond",
      "value": 71.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-05-26",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-01-20",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-V3 (Mar 2025)",
      "model_version": "DeepSeek-V3 (Mar 2025)",
      "benchmark_id": "gpqa-diamond",
      "value": 67.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-04-01",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-03-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-R1 (May 2025)",
      "model_version": "DeepSeek-R1 (May 2025)",
      "benchmark_id": "gpqa-diamond",
      "value": 76.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-05-29",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-05-28",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-V3.2",
      "model_version": "DeepSeek-V3.2",
      "benchmark_id": "gpqa-diamond",
      "value": 83.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-12-16",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-12-01",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-V4-Pro",
      "model_version": "DeepSeek-V4-Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 90.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-06",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-04-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek V4 Flash 0731",
      "model_version": "DeepSeek V4 Flash 0731",
      "benchmark_id": "gpqa-diamond",
      "value": 91,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-02",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-07-31",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek V4 Pro 0813",
      "model_version": "DeepSeek V4 Pro 0813",
      "benchmark_id": "gpqa-diamond",
      "value": 91.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-18",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-08-13",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek V4.1 Flash",
      "model_version": "DeepSeek V4.1 Flash",
      "benchmark_id": "gpqa-diamond",
      "value": 89.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-10-09",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-09-09",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek V4.1 Flash 1017",
      "model_version": "DeepSeek V4.1 Flash 1017",
      "benchmark_id": "gpqa-diamond",
      "value": 93.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-10-19",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-10-17",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Kimi K2 Thinking",
      "model_version": "Kimi K2 Thinking",
      "benchmark_id": "gpqa-diamond",
      "value": 84.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-11-11",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-11-06",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Moonshot",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Kimi K2.5",
      "model_version": "Kimi K2.5",
      "benchmark_id": "gpqa-diamond",
      "value": 87.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-02-02",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-01-27",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Moonshot",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Kimi K2.6",
      "model_version": "Kimi K2.6",
      "benchmark_id": "gpqa-diamond",
      "value": 90.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-05-01",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-04-20",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Moonshot",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Kimi K2.7 Code",
      "model_version": "Kimi K2.7 Code",
      "benchmark_id": "gpqa-diamond",
      "value": 87.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-06-12",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Moonshot",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Kimi K3",
      "model_version": "Kimi K3",
      "benchmark_id": "gpqa-diamond",
      "value": 93.1,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-07-16",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-07-16",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Moonshot",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Kimi K3.1 Pro",
      "model_version": "Kimi K3.1 Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 94.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-11-06",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-10-23",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Moonshot",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GLM-4.7",
      "model_version": "GLM-4.7",
      "benchmark_id": "gpqa-diamond",
      "value": 83.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-01-29",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-12-22",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Z.ai (Zhipu AI)",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GLM-5",
      "model_version": "GLM-5",
      "benchmark_id": "gpqa-diamond",
      "value": 87.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-02-12",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-02-11",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Z.ai (Zhipu AI)",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GLM-5.1",
      "model_version": "GLM-5.1",
      "benchmark_id": "gpqa-diamond",
      "value": 89.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-10",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-04-07",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Z.ai (Zhipu AI)",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GLM-5.2",
      "model_version": "GLM-5.2",
      "benchmark_id": "gpqa-diamond",
      "value": 91.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-06-24",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-06-16",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Z.ai (Zhipu AI)",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GLM-5.3",
      "model_version": "GLM-5.3",
      "benchmark_id": "gpqa-diamond",
      "value": 90.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-24",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-08-14",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Z.ai (Zhipu AI)",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GLM-5.3-Flash",
      "model_version": "GLM-5.3-Flash",
      "benchmark_id": "gpqa-diamond",
      "value": 90.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-26",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-08-20",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Z.ai (Zhipu AI)",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen1.5-72B",
      "model_version": "Qwen1.5-72B",
      "benchmark_id": "gpqa-diamond",
      "value": 28.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-02-04",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen1.5-32B",
      "model_version": "Qwen1.5-32B",
      "benchmark_id": "gpqa-diamond",
      "value": 30.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-04-03",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen2-72B",
      "model_version": "Qwen2-72B",
      "benchmark_id": "gpqa-diamond",
      "value": 40.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-06-07",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen2.5-32B",
      "model_version": "Qwen2.5-32B",
      "benchmark_id": "gpqa-diamond",
      "value": 46.1,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-30",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-09-17",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen2.5-72B",
      "model_version": "Qwen2.5-72B",
      "benchmark_id": "gpqa-diamond",
      "value": 49.1,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-09-19",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "QwQ-32B",
      "model_version": "QwQ-32B",
      "benchmark_id": "gpqa-diamond",
      "value": 65.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-28",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-03-05",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "QWQ-Plus",
      "model_version": "QWQ-Plus",
      "benchmark_id": "gpqa-diamond",
      "value": 65.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-04-11",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-04-08",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen3-32B",
      "model_version": "Qwen3-32B",
      "benchmark_id": "gpqa-diamond",
      "value": 65.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-28",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-04-29",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Qwen 3.6 Plus",
      "model_version": "Qwen 3.6 Plus",
      "benchmark_id": "gpqa-diamond",
      "value": 88.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-03-31",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Alibaba",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-4 Turbo (Apr 2024)",
      "model_version": "GPT-4 Turbo (Apr 2024)",
      "benchmark_id": "gpqa-diamond",
      "value": 46.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-02-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-04-09",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-4o",
      "model_version": "GPT-4o",
      "benchmark_id": "gpqa-diamond",
      "value": 49.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-08-06",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "o1-preview",
      "model_version": "o1-preview",
      "benchmark_id": "gpqa-diamond",
      "value": 50.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-09-12",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "o1-mini",
      "model_version": "o1-mini",
      "benchmark_id": "gpqa-diamond",
      "value": 62.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-02-13",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-09-12",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "o1",
      "model_version": "o1",
      "benchmark_id": "gpqa-diamond",
      "value": 76.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-02-13",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-12-17",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "o3-mini",
      "model_version": "o3-mini",
      "benchmark_id": "gpqa-diamond",
      "value": 77,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-02-13",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-01-31",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "o4-mini",
      "model_version": "o4-mini",
      "benchmark_id": "gpqa-diamond",
      "value": 79.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-04-16",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-04-16",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "o3",
      "model_version": "o3",
      "benchmark_id": "gpqa-diamond",
      "value": 81.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-04-16",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-04-16",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-5",
      "model_version": "GPT-5",
      "benchmark_id": "gpqa-diamond",
      "value": 86.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-10-29",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-08-07",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-5.1",
      "model_version": "GPT-5.1",
      "benchmark_id": "gpqa-diamond",
      "value": 87.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-11-13",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-11-13",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-5.2",
      "model_version": "GPT-5.2",
      "benchmark_id": "gpqa-diamond",
      "value": 91.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-12-13",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-12-11",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-5.4",
      "model_version": "GPT-5.4",
      "benchmark_id": "gpqa-diamond",
      "value": 93.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-03-06",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-03-05",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-5.4 Pro",
      "model_version": "GPT-5.4 Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 94.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-03-20",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-03-05",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "GPT-6 Astra",
      "model_version": "GPT-6 Astra",
      "benchmark_id": "gpqa-diamond",
      "value": 95.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-30",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-09-03",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "OpenAI",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude 3 Sonnet",
      "model_version": "Claude 3 Sonnet",
      "benchmark_id": "gpqa-diamond",
      "value": 40.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-02-29",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude 3 Opus",
      "model_version": "Claude 3 Opus",
      "benchmark_id": "gpqa-diamond",
      "value": 47.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-02-29",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude 3.5 Sonnet",
      "model_version": "Claude 3.5 Sonnet",
      "benchmark_id": "gpqa-diamond",
      "value": 54,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-06-20",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude 3.5 Sonnet (October 2024)",
      "model_version": "Claude 3.5 Sonnet (October 2024)",
      "benchmark_id": "gpqa-diamond",
      "value": 55.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-10-22",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude 3.7 Sonnet",
      "model_version": "Claude 3.7 Sonnet",
      "benchmark_id": "gpqa-diamond",
      "value": 79.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-05-26",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-02-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude Sonnet 4.5",
      "model_version": "Claude Sonnet 4.5",
      "benchmark_id": "gpqa-diamond",
      "value": 82.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-10-28",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-09-29",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude Opus 4.5",
      "model_version": "Claude Opus 4.5",
      "benchmark_id": "gpqa-diamond",
      "value": 86,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-11-24",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-11-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude Opus 4.6",
      "model_version": "Claude Opus 4.6",
      "benchmark_id": "gpqa-diamond",
      "value": 90.5,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-02-06",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-02-05",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude Opus 4.8",
      "model_version": "Claude Opus 4.8",
      "benchmark_id": "gpqa-diamond",
      "value": 91,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-06-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-05-28",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude Opus 5",
      "model_version": "Claude Opus 5",
      "benchmark_id": "gpqa-diamond",
      "value": 93.9,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-07-24",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-07-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Claude Sonnet 5.5",
      "model_version": "Claude Sonnet 5.5",
      "benchmark_id": "gpqa-diamond",
      "value": 95.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-09-29",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-09-28",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Anthropic",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemma 2 9B",
      "model_version": "Gemma 2 9B",
      "benchmark_id": "gpqa-diamond",
      "value": 27.5,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-06-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemma 2 27B",
      "model_version": "Gemma 2 27B",
      "benchmark_id": "gpqa-diamond",
      "value": 36.5,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-06-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 1.5 Flash",
      "model_version": "Gemini 1.5 Flash",
      "benchmark_id": "gpqa-diamond",
      "value": 47.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-09-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 1.5 Pro",
      "model_version": "Gemini 1.5 Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 57.2,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-09-24",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 2.0 Pro",
      "model_version": "Gemini 2.0 Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 65.7,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-02-07",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-02-05",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 2.5 Pro (Mar 2025)",
      "model_version": "Gemini 2.5 Pro (Mar 2025)",
      "benchmark_id": "gpqa-diamond",
      "value": 83.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-03-31",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-03-25",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 2.5 Pro (Jun 2025)",
      "model_version": "Gemini 2.5 Pro (Jun 2025)",
      "benchmark_id": "gpqa-diamond",
      "value": 85.3,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-11-16",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-06-17",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 3 Pro",
      "model_version": "Gemini 3 Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 92.6,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-11-19",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-11-18",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 3.1 Pro",
      "model_version": "Gemini 3.1 Pro",
      "benchmark_id": "gpqa-diamond",
      "value": 94.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-06",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-02-19",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 3.7 Flash",
      "model_version": "Gemini 3.7 Flash",
      "benchmark_id": "gpqa-diamond",
      "value": 94.8,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-14",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-08-13",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 3.8 Flash",
      "model_version": "Gemini 3.8 Flash",
      "benchmark_id": "gpqa-diamond",
      "value": 95.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-09-02",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-09-02",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "Gemini 4 Argon",
      "model_version": "Gemini 4 Argon",
      "benchmark_id": "gpqa-diamond",
      "value": 96.4,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-10-13",
      "retrieved_date": "2026-11-10",
      "release_date": "2026-09-30",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "Google DeepMind",
      "country": "US",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-V3",
      "model_version": "DeepSeek-V3",
      "benchmark_id": "gpqa-diamond",
      "value": 56.5,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2025-01-27",
      "retrieved_date": "2026-11-10",
      "release_date": "2024-12-26",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    },
    {
      "model_name": "DeepSeek-R1-Distill-Qwen-32B",
      "model_version": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark_id": "gpqa-diamond",
      "value": 64.1,
      "unit": "%",
      "source_id": "epoch",
      "source_url": "https://epoch.ai/benchmarks",
      "measured_date": "2026-08-28",
      "retrieved_date": "2026-11-10",
      "release_date": "2025-01-20",
      "measured_by": "Epoch AI",
      "license": "CC-BY-4.0",
      "independent": true,
      "organization": "DeepSeek",
      "country": "CN",
      "setting": "melhor execução por modelo"
    }
  ]
}
