PolicyBench
Grok 4.5
xAI · AI alone, no tools
United States rank
#5 of 24
US exact
80.9%
United States
United States benchmark
Exact match
80.9%
Bounded score
91.5%
Parse rate
100.0%
Eligibility flags
963/984
Score by programhardest first
| Program | Exact | Within 1% | n |
|---|---|---|---|
| Federal tax before refundable credits | 48.0% | 49.0% | 100 |
| State tax before refundable credits | 57.0% | 58.0% | 100 |
| State refundable credits | 78.0% | 78.0% | 100 |
| SNAP | 79.0% | 80.0% | 100 |
| Payroll tax | 85.0% | 88.0% | 100 |
| Federal refundable credits | 87.0% | 89.0% | 100 |
| Person-level Medicaid eligibility | 93.8% | 93.8% | 177 |
| SSI | 97.0% | 98.0% | 100 |
| Person-level Medicare eligibility | 97.7% | 97.7% | 177 |
| Free school meals eligibility | 98.0% | 98.0% | 100 |
| Reduced-price school meals eligibility | 98.0% | 98.0% | 100 |
| Person-level CHIP eligibility | 98.9% | 98.9% | 177 |
| TANF | 99.0% | 99.0% | 100 |
| Local income tax | 100.0% | 100.0% | 100 |
| Person-level Early Head Start eligibility | 100.0% | 100.0% | 38 |
| Person-level Head Start eligibility | 100.0% | 100.0% | 38 |
| Person-level WIC eligibility | 100.0% | 100.0% | 177 |
| Self-employment tax | 100.0% | 100.0% | 100 |
Hardest casesworst misses on positive references
- Federal tax before refundable credits709% offReference $1,346 · predicted $10,882Inspect household #039
- Federal tax before refundable credits489% offReference $500 · predicted $2,945Inspect household #046
- SNAP433% offReference $461 · predicted $2,457Inspect household #023
- State tax before refundable credits292% offReference $514 · predicted $2,019Inspect household #039
- Federal tax before refundable credits129% offReference $5,200 · predicted $11,919Inspect household #123
- Federal tax before refundable credits117% offReference $1,649 · predicted $3,581Inspect household #037
Scores are from the frozen manuscript snapshot under the AI-alone condition: one structured response per household, no tools, graded against PolicyEngine reference outputs. See the leaderboard and paper for methodology.