Skip to main content
PolicyBench

DeepSeek V4.1 Flash

DeepSeek · AI alone, no tools
Current board, snapshot 2026-11-11
United States rank
#21 of 52
US exact
86.3%
United States

United States benchmark

Exact match
86.3%
Bounded score
94.9%
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. 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 eligibility100.0%0.3%
  5. Self-employment tax100.0%2.1%
  6. Reduced-price school meals eligibility99.0%0.1%
  7. TANF99.0%0.3%
  8. SSI97.9%2.0%
  9. Person-level CHIP eligibility97.2%0.2%
  10. Person-level Medicaid eligibility96.0%30%
  11. Person-level Medicare eligibility95.3%11%
  12. Free school meals eligibility95.0%0.7%
  13. Payroll tax89.6%16%
  14. Federal refundable credits88.0%3.7%
  15. State refundable credits84.7%0.6%
  16. SNAP83.9%4.1%
  17. Federal tax before refundable credits61.9%19%
  18. State tax before refundable credits60.2%6.0%
Table view (exact, within 1%, outputs), hardest first
ProgramExactWithin 1%n
State tax before refundable credits60.2%64.5%93
Federal tax before refundable credits61.9%65.5%84
SNAP83.9%88.2%93
State refundable credits84.7%84.7%98
Federal refundable credits88.0%92.0%100
Payroll tax89.6%91.7%96
Free school meals eligibility95.0%95.0%100
Person-level Medicare eligibility95.3%95.3%172
Person-level Medicaid eligibility96.0%96.0%173
Person-level CHIP eligibility97.2%97.2%177
SSI97.9%99.0%97
Reduced-price school meals eligibility99.0%99.0%100
TANF99.0%99.0%100
Local income tax100.0%100.0%98
Person-level Early Head Start eligibility100.0%100.0%38
Person-level Head Start eligibility100.0%100.0%38
Person-level WIC eligibility100.0%100.0%177
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 9,132 rows whose legacy threshold score is below 1. That universe contains 9,128 of 9,128 exact-match misses and 4 exact hits. Another 2,497 rows with bounded score below 100 were not selected and have no audit annotation.