Skip to main content
PolicyBench

Gemini 4 Argon

Google · AI alone, no tools
Current board, snapshot 2026-10-14
United States rank
#12 of 50
US exact
88.7%
United States

United States benchmark

Exact match
88.7%
Bounded score
96.4%
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. Reduced-price school meals eligibility99.0%0.1%
  7. Self-employment tax99.0%2.1%
  8. TANF99.0%0.3%
  9. Person-level Medicare eligibility98.8%11%
  10. Free school meals eligibility98.0%0.7%
  11. SSI97.9%2.0%
  12. Person-level Medicaid eligibility96.5%30%
  13. Payroll tax90.6%16%
  14. Federal refundable credits90.0%3.7%
  15. SNAP84.9%4.1%
  16. State refundable credits83.8%0.6%
  17. State tax before refundable credits69.9%6.0%
  18. Federal tax before refundable credits69.0%19%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
Federal tax before refundable credits69.0%72.6%84
State tax before refundable credits69.9%74.2%93
State refundable credits83.8%83.8%99
SNAP84.9%87.1%93
Federal refundable credits90.0%92.0%100
Payroll tax90.6%92.7%96
Person-level Medicaid eligibility96.5%96.5%173
SSI97.9%99.0%97
Free school meals eligibility98.0%98.0%100
Person-level Medicare eligibility98.8%98.8%172
Reduced-price school meals eligibility99.0%99.0%100
Self-employment tax99.0%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

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.