Skip to main content
PolicyBench

Gemini 3.1 Pro Preview

Google · AI alone, no tools
Current board, snapshot 2026-09-30
United States rank
#27 of 46
US exact
82.8%
United States

United States benchmark

Exact match
82.8%
Bounded score
93.1%
Parse rate
100.0%
Eligibility flags
962/975

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. Reduced-price school meals eligibility100.0%0.1%
  4. Self-employment tax100.0%2.1%
  5. Person-level WIC eligibility99.4%0.3%
  6. Person-level Medicare eligibility99.4%11%
  7. Free school meals eligibility99.0%0.7%
  8. TANF99.0%0.3%
  9. Person-level CHIP eligibility98.3%0.2%
  10. Person-level Medicaid eligibility97.1%30%
  11. SSI96.9%2.0%
  12. Person-level Head Start eligibility94.7%1.2%
  13. Federal refundable credits86.7%3.7%
  14. SNAP83.9%4.1%
  15. State refundable credits82.7%0.6%
  16. Payroll tax68.4%16%
  17. State tax before refundable credits65.9%6.0%
  18. Federal tax before refundable credits54.4%19%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
Federal tax before refundable credits54.4%55.7%79
State tax before refundable credits65.9%67.1%85
Payroll tax68.4%69.5%95
State refundable credits82.7%82.7%98
SNAP83.9%83.9%93
Federal refundable credits86.7%89.8%98
Person-level Head Start eligibility94.7%94.7%38
SSI96.9%96.9%97
Person-level Medicaid eligibility97.1%97.1%173
Person-level CHIP eligibility98.3%98.3%177
Free school meals eligibility99.0%99.0%100
TANF99.0%99.0%100
Person-level Medicare eligibility99.4%99.4%172
Person-level WIC eligibility99.4%99.4%177
Local income tax100.0%100.0%100
Person-level Early Head Start eligibility100.0%100.0%38
Reduced-price school meals eligibility100.0%100.0%100
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 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.