Skip to main content
PolicyBench

Muse Spark 1.3

Meta · AI alone, no tools
Current board, snapshot 2026-10-14
United States rank
#18 of 50
US exact
87.2%
United States

United States benchmark

Exact match
87.2%
Bounded score
97.0%
Parse rate
100.0%
Eligibility flags
956/975

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 Early Head Start eligibility100.0%3.1%
  3. Person-level Head Start eligibility100.0%1.2%
  4. Self-employment tax100.0%2.1%
  5. Person-level WIC eligibility99.4%0.3%
  6. TANF99.0%0.3%
  7. SSI99.0%2.0%
  8. Person-level Medicare eligibility98.3%11%
  9. Free school meals eligibility98.0%0.7%
  10. Reduced-price school meals eligibility98.0%0.1%
  11. Person-level CHIP eligibility97.2%0.2%
  12. Person-level Medicaid eligibility96.5%30%
  13. Payroll tax91.7%16%
  14. Federal refundable credits88.0%3.7%
  15. SNAP86.0%4.1%
  16. State refundable credits80.8%0.6%
  17. Federal tax before refundable credits61.9%19%
  18. State tax before refundable credits58.1%6.0%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
State tax before refundable credits58.1%61.3%93
Federal tax before refundable credits61.9%69.0%84
State refundable credits80.8%80.8%99
SNAP86.0%87.1%93
Federal refundable credits88.0%91.0%100
Payroll tax91.7%94.8%96
Person-level Medicaid eligibility96.5%96.5%173
Person-level CHIP eligibility97.2%97.2%177
Free school meals eligibility98.0%98.0%100
Reduced-price school meals eligibility98.0%98.0%100
Person-level Medicare eligibility98.3%98.3%172
SSI99.0%99.0%97
TANF99.0%99.0%100
Person-level WIC eligibility99.4%99.4%177
Local income tax100.0%100.0%98
Person-level Early Head Start eligibility100.0%100.0%38
Person-level Head Start eligibility100.0%100.0%38
Self-employment tax100.0%100.0%100

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.