Skip to main content
PolicyBench

Inkling

Thinking Machines · AI alone, no tools
Current board, snapshot 2026-10-27
United States rank
#16 of 51
US exact
87.7%
United States

United States benchmark

Exact match
87.7%
Bounded score
96.3%
Parse rate
100.0%
Eligibility flags
964/975

Exact match by programall 18 output groups, best first

Bar length is the unweighted exact-match rate on that program's outputs; the right column is the program's share of the headline weight, which follows household dollars, so the bars do not average to the headline.

  1. Person-level CHIP eligibility100.0%0.2%
  2. Person-level Early Head Start eligibility100.0%3.1%
  3. Person-level Head Start eligibility100.0%1.2%
  4. Person-level Medicare eligibility100.0%11%
  5. Reduced-price school meals eligibility99.0%0.1%
  6. Self-employment tax99.0%2.1%
  7. TANF99.0%0.3%
  8. Local income tax99.0%0.3%
  9. SSI99.0%2.0%
  10. Person-level WIC eligibility98.9%0.3%
  11. Person-level Medicaid eligibility97.7%30%
  12. Free school meals eligibility96.0%0.7%
  13. Federal refundable credits87.0%3.7%
  14. SNAP84.9%4.1%
  15. Payroll tax83.3%16%
  16. State refundable credits82.8%0.6%
  17. Federal tax before refundable credits71.4%19%
  18. State tax before refundable credits55.9%6.0%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
State tax before refundable credits55.9%59.1%93
Federal tax before refundable credits71.4%77.4%84
State refundable credits82.8%82.8%99
Payroll tax83.3%86.5%96
SNAP84.9%89.2%93
Federal refundable credits87.0%91.0%100
Free school meals eligibility96.0%96.0%100
Person-level Medicaid eligibility97.7%97.7%173
Person-level WIC eligibility98.9%98.9%177
SSI99.0%99.0%97
Local income tax99.0%99.0%98
Reduced-price school meals eligibility99.0%99.0%100
Self-employment tax99.0%99.0%100
TANF99.0%99.0%100
Person-level CHIP eligibility100.0%100.0%177
Person-level Early Head Start eligibility100.0%100.0%38
Person-level Head Start eligibility100.0%100.0%38
Person-level Medicare eligibility100.0%100.0%172

Hardest casesworst misses on positive references

Scores are from the frozen manuscript snapshot under the AI-alone condition: structured responses over the same household facts (whole-scenario or in output subsets, per the serving-configuration table), no tools, graded against PolicyEngine reference outputs. See the leaderboard and paper for methodology. The frozen US annotations cover 9,050 rows whose legacy threshold score is below 1. That universe contains 9,046 of 9,046 exact-match misses and 4 exact hits. Another 2,407 rows with bounded score below 100 were not selected and have no audit annotation.