AI coding agents · scenario rankings

Attribute probe: Chinese-language teams / usable in mainland China

Most Popular AI Coding Agents for Chinese-Language Teams

This cell adds a qualifier to the question (suits Chinese-language work / usable in China). It measures conditional retrieval: who comes up under that condition, not who is better.

Concentrated

Measured 2026-09-22 · 12-seat model panel · 10 scenarios · methodology #2 v2026-09-22.1

Download image (with QR code)Share on X Share on LinkedIn

WeChat: save the image and long-press the QR code in a chat.

The ten

Rank	Entity	Mention rate (of answers)	Wilson 95% interval	Seats that mentioned it	Seats with stable coverage
1	GitHub Copilot	98.9%	[96.0%, 99.7%]	12 of 12	12 of 12
2	Cursor	97.2%	[93.5%, 98.8%]	12 of 12	12 of 12
3	Tongyi Lingma	94.3%	[89.9%, 96.9%]	12 of 12	12 of 12
4	Baidu Comate	90.9%	[85.7%, 94.3%]	12 of 12	12 of 12
5	CodeGeeX	83.0%	[76.7%, 87.8%]	12 of 12	11 of 12
6	Windsurf (Devin Desktop)	75.6%	[68.7%, 81.3%]	12 of 12	11 of 12
7	Trae	55.1%	[47.7%, 62.3%]	12 of 12	6 of 12
8	Tabnine	35.2%	[28.6%, 42.5%]	10 of 12	4 of 12
9	Claude Code	33.0%	[26.4%, 40.2%]	8 of 12	4 of 12
10	MarsCode	33.0%	[26.4%, 40.2%]	10 of 12	3 of 12

How it is counted: mention rate = answers naming it ÷ 176 (5 phrasings × 3 repeats × 12 seats = 180 calls, 176 valid); the last two columns count seats, and "stable coverage" means more than half of that seat's 15 answers. Different denominators, so 12 of 12 next to a rate below 100% is not a contradiction.

The sample behind this cell

Valid samples / calls expected: 176 / 180
Completeness: 97.8%
Effective entities (effN): 16.3
Entities mentioned at least once: 73

How this cell was asked

This cell used 5 phrasings, each asked 3 times. Every call asked for the ten names only — no reasons, no scores.

Most Popular AI Coding Agents for Chinese-Language Teams
AI coding agents that work well for Chinese-language teams?
Our developers mostly write and read Chinese. Which AI coding agents handle that well?
ai coding agent chinese language support
List some AI coding agents that are commonly used by teams working in Chinese.

Where this page stops

This is one measurement, not a trend line. The next run of the same phrasings comes next quarter.
Each call collected ten names at most. Anything past the tenth name is invisible in this cell, which is not the same as being absent.
Mention rate is the share of samples in this cell where a name came up. It is not market share, and it is not a judgement about the product.

Methodology: the panel, the phrasings and how completeness is counted

You can also query this data from Claude, Cursor or another agent, with the same reading rules attached. For agents →