TaxPraBen - TaxRead: leaderboard
TaxPraBen (2026) is a Chinese tax-practice benchmark spanning tax knowledge memorization, understanding and application, evaluated zero-shot. This board is exact-match accuracy in percent on tax reading comprehension; higher is better.
Metric: Exact-match accuracy (%) on TaxRead (tax reading comprehension, exact match, 1,000 items) in TaxPraBen, zero-shot, Chinese prompts written and rated by tax-domain annotators; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 7B (TaxPraBen checkpoint unspecified) | 84.8 | |
| 2 | GPT-3.5 Turbo | 84.3 | #3076 |
| 3 | ERNIE-3.5 | 84.1 | |
| 4 | Grok 3 | 83.8 | #614 |
| 5 | GPT-4o | 83.2 | #754 |
| 6 | chatglm3-6B | 80.6 | #8290 |
| 7 | DeepSeek-R1-Distill-Qwen-7B | 70.2 | #7976 |
| 8 | Yi-6B (TaxPraBen checkpoint unspecified) | 69.4 | |
| 9 | Bayling2 | 65.8 | |
| 10 | TaxPraBen GLM-4-9B (checkpoint unspecified) | 62.6 | |
| 11 | Mistral-V0.3 (TaxPraBen checkpoint unspecified) | 55.8 | |
| 12 | YAYI2-30B | 55.4 | |
| 13 | Atom (TaxPraBen checkpoint unspecified) | 53.3 | |
| 14 | TaxPraBen DeepSeekllm (checkpoint unspecified) | 42.1 | |
| 15 | ChnLLaMA3 (TaxPraBen checkpoint unspecified) | 29.1 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=taxpraben-taxread · How It Works · Data refreshed daily, snapshot 2026-11-22.