Adam1010
/

goodhart-gap-benchmark

execution-vs-understanding

Model card Files Files and versions

goodhart-gap-benchmark / results

114 kB

1 contributor

History: 1 commit

Adam1010's picture

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis

b684ab3 verified 20 days ago

claude-3-5-haiku-latest_20260103_182323_results.jsonl

1.31 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
claude-3-5-haiku-latest_20260103_182323_summary.json

289 Bytes

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
claude-3-5-haiku-latest_20260103_184241_results.jsonl

33.5 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
claude-3-5-haiku-latest_20260103_184241_summary.json

1.34 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
claude-sonnet-4-20250514_20260103_184954_results.jsonl

27.8 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
claude-sonnet-4-20250514_20260103_184954_summary.json

1.33 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
gpt-4o-mini_20260103_184617_results.jsonl

22.9 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
gpt-4o-mini_20260103_184617_summary.json

1.36 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
gpt-4o_20260103_184426_results.jsonl

23 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago
gpt-4o_20260103_184426_summary.json

1.32 kB

v1.1: Financial domain audit - confirms Goodhart Gap hypothesis 20 days ago