PolicyBench - US Exact Match - payroll_tax: leaderboard

The payroll_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: Around February 2027. 52 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6 Sol100#29
2GPT-6.1 Terra98.96#22
3Claude Opus 5.595.83#7
4GPT-5.6 Sol94.79#33
5Claude Sonnet 5.594.79#21
6Grok 4.793.75#48
7Kimi K392.71#59
8GPT-6 Luna92.71#105
9Claude Fable 5.191.67#17
10Muse Spark 1.391.67#45
11Muse Wonder91.67#31
12GLM-5.3 Flash90.63#136
13GPT-5.6 Luna90.63#130
14Gemini 4 Argon90.63#14
15Grok 4.690.63#47

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-payroll-tax · How It Works · Data refreshed daily, snapshot 2026-11-17.