Skip to main content
PolicyBench

Gemini 3.7 Flash

Google · AI alone, no tools
Current board, snapshot 2026-09-30
United States rank
#24 of 46
US exact
84.2%
United States

United States benchmark

Exact match
84.2%
Bounded score
93.6%
Parse rate
100.0%
Eligibility flags
961/975

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. Person-level Medicare eligibility100.0%11%
  5. Self-employment tax100.0%2.1%
  6. Person-level WIC eligibility99.4%0.3%
  7. Free school meals eligibility99.0%0.7%
  8. Reduced-price school meals eligibility99.0%0.1%
  9. TANF99.0%0.3%
  10. SSI97.9%2.0%
  11. Person-level CHIP eligibility97.2%0.2%
  12. Person-level Medicaid eligibility96.5%30%
  13. Federal refundable credits85.7%3.7%
  14. SNAP83.9%4.1%
  15. State refundable credits83.7%0.6%
  16. Payroll tax73.7%16%
  17. State tax before refundable credits69.4%6.0%
  18. Federal tax before refundable credits57.0%19%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
Federal tax before refundable credits57.0%58.2%79
State tax before refundable credits69.4%72.9%85
Payroll tax73.7%73.7%95
State refundable credits83.7%82.7%98
SNAP83.9%83.9%93
Federal refundable credits85.7%87.8%98
Person-level Medicaid eligibility96.5%96.5%173
Person-level CHIP eligibility97.2%97.2%177
SSI97.9%99.0%97
Free school meals eligibility99.0%99.0%100
Reduced-price school meals eligibility99.0%99.0%100
TANF99.0%99.0%100
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
Person-level Head Start eligibility100.0%100.0%38
Person-level Medicare eligibility100.0%100.0%172
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.