Skip to main content
PolicyBench

DeepSeek V4 Flash 0731

DeepSeek · AI alone, no tools
Current board, snapshot 2026-09-05
United States rank
#16 of 39
US exact
79.7%
United States

United States benchmark

Exact match
79.7%
Bounded score
91.5%
Parse rate
100.0%
Eligibility flags
962/979

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 WIC eligibility99.4%0.3%
  5. Person-level Medicare eligibility99.4%11%
  6. Self-employment tax99.0%2.1%
  7. TANF99.0%0.3%
  8. Person-level CHIP eligibility98.3%0.2%
  9. Free school meals eligibility98.0%0.7%
  10. Reduced-price school meals eligibility98.0%0.1%
  11. SSI97.9%2.0%
  12. Person-level Medicaid eligibility95.5%30%
  13. Federal refundable credits81.0%3.7%
  14. SNAP79.4%4.1%
  15. Payroll tax79.0%16%
  16. State refundable credits78.0%0.6%
  17. Federal tax before refundable credits48.0%19%
  18. State tax before refundable credits46.0%6.0%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
State tax before refundable credits46.0%50.0%100
Federal tax before refundable credits48.0%49.0%100
State refundable credits78.0%78.0%100
Payroll tax79.0%81.0%100
SNAP79.4%81.4%97
Federal refundable credits81.0%84.0%100
Person-level Medicaid eligibility95.5%95.5%177
SSI97.9%100.0%97
Free school meals eligibility98.0%98.0%100
Reduced-price school meals eligibility98.0%98.0%100
Person-level CHIP eligibility98.3%98.3%177
Self-employment tax99.0%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
Person-level Head Start eligibility100.0%100.0%38

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 8,783 rows whose legacy threshold score is below 1. That universe contains 8,780 of 8,780 exact-match misses and 3 exact hits. Another 1,605 rows with bounded score below 100 were not selected and have no audit annotation.