PolicyBench - US Exact Match - person_medicaid_eligible: leaderboard
The person_medicaid_eligible output of PolicyBench US, without tools. Read countries.us.heatmap exact, with the native common per-output denominator and symmetric reference exclusions. Aggregate programStats rows across models are not model scores. Metric: Exact match (%). Source: https://policybench.org
Metric: Exact match (%). Source: policybench.org. Saturation forecast: Estimated already saturated. 52 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 99.42 | #8 |
| 2 | Claude Opus 5.5 | 97.69 | #7 |
| 3 | GPT-6 Luna | 97.69 | #105 |
| 4 | Grok 4.7 | 97.69 | #48 |
| 5 | GPT-6 Sol | 97.69 | #29 |
| 6 | GPT-6.1 Terra | 97.69 | #22 |
| 7 | Inkling | 97.69 | #282 |
| 8 | Claude Fable 5.2 | 97.69 | #1 |
| 9 | Gemini 3.1 Pro (Preview) | 97.11 | #99 |
| 10 | GPT-5.6 Sol | 97.11 | #33 |
| 11 | Gemini 3.8 Flash | 97.11 | #39 |
| 12 | Claude Fable 5.1 | 97.11 | #17 |
| 13 | Muse Wonder | 97.11 | #31 |
| 14 | GPT-5.5 | 96.53 | #50 |
| 15 | Gemini 3.5 Flash | 96.53 | #107 |
No result here: #2 GPT-6.2 Astra, #3 Gemini 4 Carbon, #6 GPT-6.2 Sol.
Interactive version: theaggregate.ai/benchmark?slug=policybench-us-exact-match-person-medicaid-eligible · How It Works · Data refreshed daily, snapshot 2026-11-17.