> ## 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.

# China's top AI model trailed the top US model by 39 Arena points in March 2026, down from 346 in 2023
- URL: https://aiadoption.org/data/arena-us-vs-china-top-models/
- Published: 2026-10-19T15:55:50.000Z
- Updated: 2026-10-21T06:02:39.000Z
- Description: The top Chinese model on the Arena scored 1,464 in March 2026, 39 points behind the top US model (1,503). The gap was 346 points in May 2023 and 5 in February 2025.
- Author: Manu
- Tags: Data, AI Models, Large Language Models, AI in the US, AI in China, #chart, #ai-index-2026, #hub-models, #lens-us-china, #country-us, #country-china

1,464

▲ 50% since May 2023

Arena score of the top Chinese model in March 2026, 39 points behind the top US model (1,503)

20232026

## What the chart shows

In May 2023 the top US model on the Arena led the top Chinese model by 346 points. By February 2025 the gap had shrunk to 5 points (1,405 against 1,400), the smallest in the data. In March 2026 the top US model scored 1,503 and the top Chinese model 1,464, a gap of 39 points (2.7%).

Since January 2025 the gap has moved between 5 and 91 points, and the top Chinese model has not led in any month of the data. The report names Claude Opus 4.6 and Dola-Seed-2.0 Preview as the leaders in March 2026.

## Key numbers

| Measure                     | Value |
| --------------------------- | ----- |
| Top US model, Mar 2026      | 1,503 |
| Top Chinese model, Mar 2026 | 1,464 |
| Gap, Mar 2026               | 39    |
| Gap, May 2023               | 346   |
| Smallest gap, Feb 2025      | 5     |

## How to read it

- Each point is the highest score of any US or Chinese model that month on the Arena’s historical leaderboard (public, style control on), exported in March 2026.
- Arena scores reflect user preferences in blind comparisons, not accuracy on a fixed test. Model names come from the report text; the data gives scores only.
- Arena scores have no true zero, so the vertical axis starts at 900 to show the gaps; compare differences between lines, not their heights above the axis.

**Source:** [Arena](https://aiadoption.org/sources/#arena), 2026, via the AI Index Report 2026 (Stanford HAI), figure 2.1.3: *Performance of top United States vs. Chinese models on the Arena*. 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/arena-us-vs-china-top-models.csv?ref=aiadoption.org) · [Cite this chart](#source)