PolicyBench - US Exact Match - person_medicare_eligible: leaderboard
The person_medicare_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 | Gemini 3.8 Flash | 100 | #39 |
| 2 | Claude Opus 5.5 | 100 | #7 |
| 3 | GPT-5.6 Terra | 100 | #68 |
| 4 | Gemini 3.7 Flash | 100 | #38 |
| 5 | Gemini 3.6 Flash | 100 | #79 |
| 6 | Claude Sonnet 5.5 | 100 | #21 |
| 7 | Gemini 3.5 Flash Lite | 100 | #302 |
| 8 | GPT-6 Sol | 100 | #29 |
| 9 | Grok 4.6 | 100 | #47 |
| 10 | Inkling | 100 | #282 |
| 11 | Claude Fable 5.2 | 100 | #1 |
| 12 | Gemini 3.1 Pro (Preview) | 99.42 | #99 |
| 13 | DeepSeek V4 Pro | 99.42 | #198 |
| 14 | Gemini 3 Flash (Preview) | 99.42 | #151 |
| 15 | Gemini 3.5 Flash | 99.42 | #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-medicare-eligible · How It Works · Data refreshed daily, snapshot 2026-11-17.