> ## Content Index
> Fetch the complete content index at: https://aiadoption.org/llms.txt
> Use this file to discover other available public pages before exploring further.

# The top 15 models on TaxEval v2 scored within 2.9 percentage points of each other in early 2026
- URL: https://aiadoption.org/data/taxeval-ai-tax-accuracy/
- Published: 2026-10-19T16:06:28.000Z
- Updated: 2026-10-21T06:01:07.000Z
- Description: On TaxEval v2, over 1,500 expert-checked tax questions, Claude Sonnet 4.6 led at 77.1% in early 2026. The 15th-placed model, Kimi K2.5, scored 74.2%, just 2.9 percentage points lower.
- Author: Manu
- Tags: Data, AI Benchmarks, AI in Finance, #chart, #ai-index-2026, #hub-benchmarks, #industry-finance

2.9 pts

gap between the best (Claude Sonnet 4.6, 77.1%) and 15th-placed (Kimi K2.5, 74.2%) models on TaxEval v2

First and 15th

Claude Sonnet 4.677.1%

Kimi K2.574.2%

## What the chart shows

TaxEval v2 contains over 1,500 expert-verified tax questions covering numerical reasoning, problem solving and compliance rules, and scores both the answer and the reasoning behind it. Claude Sonnet 4.6 led the top 15 at 77.1%, ahead of Claude Opus 4.6 (Thinking) at 76% and Grok 3 at 75.9%.

The whole top 15 lies within 2.9 percentage points, down to Kimi K2.5 at 74.2%. Older models such as GPT 4o (74.5%) and o1 (74.3%) remain within the band.

## Key numbers

| Measure                    | Value                  |
| -------------------------- | ---------------------- |
| Claude Sonnet 4.6          | 77.11%                 |
| Claude Opus 4.6 (Thinking) | 75.96%                 |
| Grok 3                     | 75.88%                 |
| GPT 4o (2024-11-20)        | 74.53%                 |
| Kimi K2.5, 15th            | 74.20%                 |
| Gap, 1st to 15th           | 2.91 percentage points |

## How to read it

- The report text names Claude 3.7 Sonnet (Thinking) at 74% as the lowest of the 15; it is not in the published data, where the lowest is Kimi K2.5 at 74.2%. We use the data.
- The bars start at zero, so they look almost equal: that is the finding.
- Scores are from Vals.ai’s TaxEval v2 leaderboard; the AI Index shows the top 15 models.

**Source:** [Vals.ai](https://aiadoption.org/sources/#vals-ai), 2026, via the AI Index Report 2026 (Stanford HAI), figure 2.5.8: *TaxEval v2: accuracy*. Chart and text by AI Adoption.  
Numbers checked against the published data on 20 October 2026.  
[Download the data (CSV)](https://charts.aiadoption.org/ai-index/csv/taxeval-ai-tax-accuracy.csv?ref=aiadoption.org) · [Cite this chart](#source)