Agentic AI Atlas

II.

TestSet JSON

test-set:toolbench-tooleval

Structured · live

ToolBench ToolEval suite json

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

File · benchmarks/test-sets/source-backed-benchmark-test-sets.yamlCluster · benchmarks

Record JSON

{
  "id": "test-set:toolbench-tooleval",
  "_kind": "TestSet",
  "_file": "benchmarks/test-sets/source-backed-benchmark-test-sets.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "ToolBench ToolEval suite",
    "benchmarkId": "benchmark:toolbench",
    "releasedAt": "2023-07-31",
    "composition": "ToolBench/ToolEval artifact for evaluating LLM tool-use trajectories\nover real-world API instructions, with pass-rate and win-rate scoring.\n",
    "homepageUrl": "https://github.com/OpenBMB/ToolBench",
    "description": "Canonical ToolBench evaluation artifact for API tool-use benchmarks.\n"
  },
  "outgoingEdges": [
    {
      "from": "test-set:toolbench-tooleval",
      "to": "benchmark:toolbench",
      "kind": "belongs_to_benchmark"
    }
  ],
  "incomingEdges": []
}