Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Adam1010
/
goodhart-gap-benchmark

English
benchmark
reasoning
multi-step
evaluation
llm-evaluation
goodhart
execution-vs-understanding
consensus
multi-model
Model card Files Files and versions
xet
Community
goodhart-gap-benchmark / data
91 MB
  • 1 contributor
History: 2 commits
Adam1010's picture
Adam1010
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
ca5e3d7 verified 9 days ago
  • baseline_results.json
    2.14 kB
    v1.1: Document financial domain findings - strongest Goodhart Gap detector 9 days ago
  • combined_summary.json
    476 Bytes
    v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested) 9 days ago
  • combined_test.jsonl
    16.9 MB
    xet
    v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested) 9 days ago
  • goodhart_contested.jsonl
    17 MB
    xet
    v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested) 9 days ago
  • goodhart_disagreements.jsonl
    57.1 MB
    xet
    v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested) 9 days ago
  • summary.json
    443 Bytes
    v1.1: Document financial domain findings - strongest Goodhart Gap detector 9 days ago
  • test.jsonl
    44.6 kB
    v1.1: Document financial domain findings - strongest Goodhart Gap detector 9 days ago