.eval_results/parsebench.yaml

- dataset:
    id: llamaindex/ParseBench
    task_id: mean
  value: 76.36
  date: '2026-06-12'
  source:
    url: https://huggingface.co/datasets/llamaindex/ParseBench
    name: ParseBench
    user: Haigini
  notes: "Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49). Full-set single-pass run (2,553 test cases, 0 failures): vLLM serving of the public weights + the deterministic provider pipeline. Layout dimension = layout_element_rule_pass_rate (official leaderboard metric), as re-measured by the ParseBench maintainers on this provider's predictions with the Chart/Flowchart label mapping (run-llama/ParseBench PR #49). Reproducible end-to-end with the provider in the PR."
- dataset:
    id: llamaindex/ParseBench
    task_id: table
  value: 85.56
  date: '2026-06-12'
  source:
    url: https://huggingface.co/datasets/llamaindex/ParseBench
    name: ParseBench
    user: Haigini
  notes: "Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49)"
- dataset:
    id: llamaindex/ParseBench
    task_id: layout
  value: 78.84
  date: '2026-06-12'
  source:
    url: https://huggingface.co/datasets/llamaindex/ParseBench
    name: ParseBench
    user: Haigini
  notes: "Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49)"
- dataset:
    id: llamaindex/ParseBench
    task_id: text_content
  value: 87.19
  date: '2026-06-12'
  source:
    url: https://huggingface.co/datasets/llamaindex/ParseBench
    name: ParseBench
    user: Haigini
  notes: "Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49)"
- dataset:
    id: llamaindex/ParseBench
    task_id: text_formatting
  value: 66.81
  date: '2026-06-12'
  source:
    url: https://huggingface.co/datasets/llamaindex/ParseBench
    name: ParseBench
    user: Haigini
  notes: "Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49)"
- dataset:
    id: llamaindex/ParseBench
    task_id: chart
  value: 63.41
  date: '2026-06-12'
  source:
    url: https://huggingface.co/datasets/llamaindex/ParseBench
    name: ParseBench
    user: Haigini
  notes: "Pipeline name: kdl_frontier_nano (standalone provider, run-llama/ParseBench PR #49)"