{
  "id": "benchmark:human-eval",
  "_kind": "Benchmark",
  "_file": "benchmarks/benchmarks/human-eval.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "HumanEval",
    "homepageUrl": "https://github.com/openai/human-eval",
    "kind": "function-completion",
    "targetsKind": "ModelVersion",
    "description": "Hand-written programming problems for evaluating code generation.\n"
  },
  "outgoingEdges": [
    {
      "from": "benchmark:human-eval",
      "to": "skill-area:python-implementation",
      "kind": "covers",
      "attributes": {
        "attributes": {
          "coverage": "full",
          "weight": 0.5
        }
      }
    }
  ],
  "incomingEdges": [
    {
      "from": "eval-result:human-eval.qwen-2-5-72b.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.qwen-2-5-coder-32b.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.claude-sonnet-4-6.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.deepseek-v3.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.llama-4-405b.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.llama-3-1-405b.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.llama-3-3-70b.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.mistral-large-2.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.codestral-25-01.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:human-eval.gpt-5.001",
      "to": "benchmark:human-eval",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-run:human-eval.qwen-2-5-72b.2024-09",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.qwen-2-5-coder-32b.2024-11",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.claude-sonnet-4-6.2025-11",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.deepseek-v3.2024-12",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.llama-4-405b.2024-07",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.llama-3-1-405b.2024-07",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.llama-3-3-70b.2024-12",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.mistral-large-2.2024-07",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.codestral-25-01.2025-01",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:human-eval.gpt-5.2025-08",
      "to": "benchmark:human-eval",
      "kind": "for_benchmark"
    },
    {
      "from": "scope-boundary:human-eval.scope",
      "to": "benchmark:human-eval",
      "kind": "bounds_subject"
    }
  ]
}