Skip to main content
PolicyBench

Gemini 3.1 Flash Lite Preview

Google · AI alone, no tools
Current board, snapshot 2026-09-30
United States rank
#35 of 46
US exact
80.9%
United States

United States benchmark

Exact match
80.9%
Bounded score
89.2%
Parse rate
100.0%
Eligibility flags
949/975

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. Reduced-price school meals eligibility100.0%0.1%
  3. Free school meals eligibility99.0%0.7%
  4. Local income tax99.0%0.3%
  5. TANF99.0%0.3%
  6. Person-level WIC eligibility98.9%0.3%
  7. SSI97.9%2.0%
  8. Person-level Early Head Start eligibility97.4%3.1%
  9. Person-level Head Start eligibility97.4%1.2%
  10. Person-level Medicare eligibility96.5%11%
  11. Self-employment tax96.0%2.1%
  12. Person-level Medicaid eligibility91.3%30%
  13. SNAP84.9%4.1%
  14. Federal refundable credits84.7%3.7%
  15. State refundable credits81.6%0.6%
  16. Payroll tax80.0%16%
  17. State tax before refundable credits54.1%6.0%
  18. Federal tax before refundable credits48.1%19%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
Federal tax before refundable credits48.1%49.4%79
State tax before refundable credits54.1%56.5%85
Payroll tax80.0%88.4%95
State refundable credits81.6%81.6%98
Federal refundable credits84.7%84.7%98
SNAP84.9%84.9%93
Person-level Medicaid eligibility91.3%91.3%173
Self-employment tax96.0%98.0%100
Person-level Medicare eligibility96.5%96.5%172
Person-level Early Head Start eligibility97.4%97.4%38
Person-level Head Start eligibility97.4%97.4%38
SSI97.9%97.9%97
Person-level WIC eligibility98.9%98.9%177
Free school meals eligibility99.0%99.0%100
Local income tax99.0%99.0%100
TANF99.0%99.0%100
Person-level CHIP eligibility100.0%100.0%177
Reduced-price school meals eligibility100.0%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 7,527 rows whose legacy threshold score is below 1. That universe contains 7,523 of 7,523 exact-match misses and 4 exact hits. Another 2,072 rows with bounded score below 100 were not selected and have no audit annotation.