Skip to main content
PolicyBench

DeepSeek V4 Pro 0813

DeepSeek · AI alone, no tools
Current board, snapshot 2026-09-05
United States rank
#17 of 39
US exact
79.5%
United States

United States benchmark

Exact match
79.5%
Bounded score
91.5%
Parse rate
100.0%
Eligibility flags
968/979

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 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. Self-employment tax100.0%2.1%
  6. Person-level WIC eligibility99.4%0.3%
  7. Person-level Medicare eligibility99.4%11%
  8. Free school meals eligibility99.0%0.7%
  9. Reduced-price school meals eligibility99.0%0.1%
  10. TANF99.0%0.3%
  11. SSI97.9%2.0%
  12. Person-level Medicaid eligibility96.0%30%
  13. Federal refundable credits89.0%3.7%
  14. State refundable credits80.0%0.6%
  15. SNAP79.4%4.1%
  16. Payroll tax79.0%16%
  17. State tax before refundable credits55.0%6.0%
  18. Federal tax before refundable credits42.0%19%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
Federal tax before refundable credits42.0%42.0%100
State tax before refundable credits55.0%61.0%100
Payroll tax79.0%84.0%100
SNAP79.4%79.4%97
State refundable credits80.0%80.0%100
Federal refundable credits89.0%91.0%100
Person-level Medicaid eligibility96.0%96.0%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 Medicare eligibility99.4%99.4%172
Person-level WIC eligibility99.4%99.4%177
Local income tax100.0%100.0%100
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
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 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.