PolicyBench - US Exact Match - free_school_meals_eligible: leaderboard
The free_school_meals_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-5.6 Sol | 97 | #33 |
| 2 | Gemini 3 Flash (Preview) | 97 | #151 |
| 3 | Gemini 3.5 Flash | 97 | #107 |
| 4 | GPT-6 Astra | 97 | #8 |
| 5 | GPT-6.1 Sol | 97 | #12 |
| 6 | GPT-6 Sol | 97 | #29 |
| 7 | Gemini 3.1 Pro (Preview) | 96 | #99 |
| 8 | Claude Opus 4.7 | 96 | #82 |
| 9 | MiniMax-M3 | 96 | #278 |
| 10 | Gemini 3.1 Flash Lite (Preview) | 96 | #418 |
| 11 | Claude Sonnet 5 | 96 | #118 |
| 12 | Qwen 3.7 Max | 96 | #156 |
| 13 | Gemini 3.7 Flash | 96 | #38 |
| 14 | Gemini 3.6 Flash | 96 | #79 |
| 15 | Claude Fable 5 | 96 | #28 |
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-free-school-meals-eligible · How It Works · Data refreshed daily, snapshot 2026-11-17.