Agentic AI Atlasby a5c.ai
OverviewWikiGraphFor AgentsEdgesSearchWorkspace
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · SWE-bench Verified
benchmark:swe-bench-verifieda5c.ai
Search record views/
Record · tabs

Available views

II.Record viewspp. 1 - 1
overviewjsongraph
II.
Benchmark JSON

benchmark:swe-bench-verified

Structured · live

SWE-bench Verified json

Inspect the normalized record payload exactly as the atlas UI reads it.

File · benchmarks/benchmarks/swe-bench-verified.yamlCluster · benchmarks
Record JSON
{
  "id": "benchmark:swe-bench-verified",
  "_kind": "Benchmark",
  "_file": "benchmarks/benchmarks/swe-bench-verified.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "SWE-bench Verified",
    "homepageUrl": "https://www.swebench.com/",
    "kind": "full-stack",
    "targetsKind": "AgentVersion",
    "description": "Human-verified subset of SWE-bench (500 cases) with cleaned task\nstatements and verified-solvable issues.\n"
  },
  "outgoingEdges": [
    {
      "from": "benchmark:swe-bench-verified",
      "to": "benchmark:swe-bench",
      "kind": "refines"
    },
    {
      "from": "benchmark:swe-bench-verified",
      "to": "skill-area:bug-fixing-from-issues",
      "kind": "covers",
      "attributes": {
        "attributes": {
          "coverage": "full",
          "weight": 0.4
        }
      }
    }
  ],
  "incomingEdges": [
    {
      "from": "eval-result:swe-bench-verified.claude-haiku-4-5.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench.deepseek-v3.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.gemini-2-5-flash.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.llama-4-405b.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench.llama-3-1-405b.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.claude-opus-4-5.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.claude-opus-4-7.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.gpt-5.headline",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.o3.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.gemini-2-5-pro.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench.claude-code.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.claude-sonnet-4-5.high-compute.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.claude-sonnet-4-5.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.gpt-5.headline.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-result:swe-bench-verified.gpt-5.001",
      "to": "benchmark:swe-bench-verified",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-run:swe-bench-verified.claude-haiku-4-5.2025-10",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench.deepseek-v3.2024-12",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.gemini-2-5-flash.2025-06",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.llama-4-405b.2024-07",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench.llama-3-1-405b.2024-07",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.claude-opus-4-5.2025-09",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.claude-opus-4-7.2026-01",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.o3.2025-04",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.gemini-2-5-pro.2025-06",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench.claude-code@1.x.2025-04-29",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.claude-sonnet-4-5.2025-09",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:swe-bench-verified.gpt-5.2025-08",
      "to": "benchmark:swe-bench-verified",
      "kind": "for_benchmark"
    },
    {
      "from": "test-set:swe-bench-verified-2024-12",
      "to": "benchmark:swe-bench-verified",
      "kind": "belongs_to_benchmark"
    },
    {
      "from": "scope-boundary:swe-bench-verified.scope",
      "to": "benchmark:swe-bench-verified",
      "kind": "bounds_subject"
    }
  ]
}

Shortcuts

Back to overview
Open graph tab