Skip to main content
PolicyBench

Muse Wonder

Meta · AI alone, no tools
Current board, snapshot 2026-10-14
United States rank
#10 of 50
US exact
90.1%
United States

United States benchmark

Exact match
90.1%
Bounded score
97.6%
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. Local income tax100.0%0.3%
  2. Person-level CHIP eligibility100.0%0.2%
  3. Person-level Early Head Start eligibility100.0%3.1%
  4. Person-level Head Start eligibility100.0%1.2%
  5. Person-level WIC eligibility100.0%0.3%
  6. Self-employment tax100.0%2.1%
  7. SSI100.0%2.0%
  8. Reduced-price school meals eligibility99.0%0.1%
  9. TANF99.0%0.3%
  10. Person-level Medicare eligibility98.3%11%
  11. Free school meals eligibility98.0%0.7%
  12. Person-level Medicaid eligibility97.1%30%
  13. Federal refundable credits92.0%3.7%
  14. Payroll tax91.7%16%
  15. SNAP87.1%4.1%
  16. State refundable credits84.8%0.6%
  17. Federal tax before refundable credits75.0%19%
  18. State tax before refundable credits64.5%6.0%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
State tax before refundable credits64.5%66.7%93
Federal tax before refundable credits75.0%88.1%84
State refundable credits84.8%84.8%99
SNAP87.1%88.2%93
Payroll tax91.7%93.8%96
Federal refundable credits92.0%94.0%100
Person-level Medicaid eligibility97.1%97.1%173
Free school meals eligibility98.0%98.0%100
Person-level Medicare eligibility98.3%98.3%172
Reduced-price school meals eligibility99.0%99.0%100
TANF99.0%99.0%100
Local income tax100.0%100.0%98
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 WIC eligibility100.0%100.0%177
Self-employment tax100.0%100.0%100
SSI100.0%100.0%97

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 8,765 rows whose legacy threshold score is below 1. That universe contains 8,761 of 8,761 exact-match misses and 4 exact hits. Another 2,329 rows with bounded score below 100 were not selected and have no audit annotation.