PolicyBench - US Exact Match - self_employment_tax: leaderboard
The self_employment_tax 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 3.1 Pro (Preview) | 100 | #99 |
| 2 | GPT-5.5 | 100 | #50 |
| 3 | Claude Opus 4.7 | 100 | #82 |
| 4 | GPT-5.6 Sol | 100 | #33 |
| 5 | Claude Opus 4.8 | 100 | #62 |
| 6 | Gemini 3.8 Flash | 100 | #39 |
| 7 | Gemini 3.5 Flash | 100 | #107 |
| 8 | GPT-6 Astra | 100 | #8 |
| 9 | DeepSeek V4.1 Flash | 100 | #69 |
| 10 | Claude Opus 5.5 | 100 | #7 |
| 11 | Gemini 3.7 Flash | 100 | #38 |
| 12 | Gemini 3.6 Flash | 100 | #79 |
| 13 | GPT-6.1 Sol | 100 | #12 |
| 14 | Claude Sonnet 5.5 | 100 | #21 |
| 15 | Grok 4.5 | 100 | #91 |
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-self-employment-tax · How It Works · Data refreshed daily, snapshot 2026-11-17.