GPT-6 Astra
United States benchmark
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.
- Free school meals eligibility100.0%0.7%
- Local income tax100.0%0.3%
- Person-level CHIP eligibility100.0%0.2%
- Person-level Early Head Start eligibility100.0%3.1%
- Person-level Head Start eligibility100.0%1.2%
- Person-level WIC eligibility100.0%0.3%
- Self-employment tax100.0%2.1%
- SSI100.0%2.0%
- Person-level Medicaid eligibility99.4%30%
- Reduced-price school meals eligibility99.0%0.1%
- TANF99.0%0.3%
- Federal refundable credits98.0%3.7%
- Person-level Medicare eligibility91.3%11%
- Payroll tax86.0%16%
- State refundable credits84.0%0.6%
- SNAP83.5%4.1%
- Federal tax before refundable credits73.0%19%
- State tax before refundable credits65.0%6.0%
Table view (exact, within 1%, outputs), hardest first
| Program | Exact | Within 1% | n |
|---|---|---|---|
| State tax before refundable credits | 65.0% | 73.0% | 100 |
| Federal tax before refundable credits | 73.0% | 77.0% | 100 |
| SNAP | 83.5% | 88.7% | 97 |
| State refundable credits | 84.0% | 84.0% | 100 |
| Payroll tax | 86.0% | 88.0% | 100 |
| Person-level Medicare eligibility | 91.3% | 91.3% | 172 |
| Federal refundable credits | 98.0% | 98.0% | 100 |
| Reduced-price school meals eligibility | 99.0% | 99.0% | 100 |
| TANF | 99.0% | 100.0% | 100 |
| Person-level Medicaid eligibility | 99.4% | 99.4% | 177 |
| Free school meals eligibility | 100.0% | 100.0% | 100 |
| Local income tax | 100.0% | 100.0% | 100 |
| Person-level CHIP eligibility | 100.0% | 100.0% | 177 |
| 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 |
| SSI | 100.0% | 100.0% | 97 |
Hardest casesworst misses on positive references
- State refundable credits4111% offReference $19 · predicted $800Inspect household #043
- Federal tax before refundable credits282% offReference $1,346 · predicted $5,145Inspect household #039
- State tax before refundable credits186% offReference $514 · predicted $1,473Inspect household #039
- State refundable credits100% offReference $40 · predicted $0Inspect household #029
- SNAP100% offReference $288 · predicted $0Inspect household #030
- State tax before refundable credits100% offReference $285 · predicted $0Inspect household #042
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.