Data Explorer

Per-model self-identification rates across languages, grouped by vendor. 261 cross-vendor confusions detected.

7,800 answers·26 models·10 languages

Run

Run summary

26 models · 10 languages

7,800

Answers

89.3%

Self-ID

3.3%

Cross-vendor

6.2%

Unknown

1.1%

Refused

Imitation balance

Per manufacturer: how often other models claim to be it (right) vs how often its own models claim to be someone else (left). Sorted by net — identity creditors at the top, debtors at the bottom. Tested manufacturers only.

OpenAI

+57

DeepSeek

+55

Qwen

+17

Google

xAI

Moonshot

MiniMax

Xiaomi

inclusionAI

z-ai

ERNIE

Anthropic

-7

StepFun

-11

Kwai

-22

Doubao

-56

Tencent

-136

imitates others ◀│▶ imitated by others

Strongest confusion pairs

The most likely directed mistakes — when a manufacturer's models claim to be a specific other manufacturer. Bar length = how often (P across all answers for the source).

Tencent→Microsoft

12.7%38/300

Tencent→

DeepSeek

10.3%31/300

Tencent→

Anthropic

8.3%25/300

Kwai→

Qwen

5.0%15/300

Doubao→

OpenAI

3.8%45/1200

Anthropic→

DeepSeek

2.6%23/900

Tencent→NAVER

2.0%6/300

Tencent→Yandex

2.0%6/300

StepFun→

Google

1.7%5/300

Doubao→Yandex

1.1%13/1200

Anthropic→

OpenAI

1.0%9/900

Tencent→

xAI

0.7%2/300

Kwai→

DeepSeek

0.7%2/300

Tencent→

Google

0.7%2/300

Tencent→

Mistral

0.7%2/300

By language

Self-ID and refusal rates per language, plus the most common cross-vendor confusion at that language.

Language	Self-ID	Refused	Top confusion
ruРусский	80.9%	1.5%	Yandex10.8%
ko한국어	83.6%	2.4%	DeepSeek30.0%
frFrançais	85.4%	3.6%	OpenAI24.2%
ptPortuguês	86.3%	0.0%	DeepSeek63.3%
ja日本語	86.4%	1.7%	Anthropic46.7%
esEspañol	87.4%	1.9%	Microsoft33.3%
zh-Hans简体中文	92.8%	0.1%	DeepSeek25.6%
enEnglish	95.4%	0.1%	Maria0.8%
deDeutsch	96.5%	0.0%	Microsoft23.3%
zh-Hant繁體中文	98.1%	0.0%	—

Answer composition by language

How the same “Who are you?” question splits into correct self-ID vs. confusion vs. abstention — per language, worst self-ID first.

Self-IDCross-vendorUnknownRefused

ruРусский

81%

ko한국어

84%

frFrançais

85%

ptPortuguês

86%

ja日本語

86%

esEspañol

87%

zh-Hans简体中文

93%

enEnglish

95%

deDeutsch

97%

zh-Hant繁體中文

98%

Language fragility

Per model, the span of self-ID rate across the 10 languages (worst-language • → best-language •). A wide span means the model's sense of identity depends heavily on the language it's asked in. Widest swing first.

ling-2.6-1t

0%ja

100%en

glm-5.1

0%ko

100%en

ring-2.6-1t

0%ja

100%en

gpt-5.5

3%en

100%ko

claude-opus-4.8

3%zh-Hans

100%en

doubao-seed-2.0-code

3%fr

100%zh-Hans

hy3-preview

3%ko

100%en

gpt-5.3-codex

13%ru

100%ko

kat-coder-pro-v2

60%ru

100%en

claude-sonnet-4.6

80%ru

100%en

step-3.7-flash

80%ru

100%en

claude-haiku-4.5

97%ko

100%en

deepseek-v4-flash

97%de

100%en

minimax-m2.7

97%en

100%zh-Hans

gemini-3.5-flash

—

100%all

grok-4.3

—

100%all

chat-latest

—

100%all

gemini-3.1-pro-preview

—

100%all

doubao-seed-2.0-mini

—

100%all

qwen3.7-max

—

100%all

mimo-v2.5-pro

—

100%all

doubao-seed-2.0-lite

—

100%all

deepseek-v4-pro

—

100%all

doubao-seed-2.0-pro

—

100%all

kimi-k2.6

—

100%all

ernie-5.1

—

100%all

worst languagemeanbest language

Abstention by manufacturer

The other failure mode — not answering wrong, but not answering: giving no identity (“unknown”) or refusing outright. Share of all answers.

Unknown (“I’m an AI”)Refused

inclusionAI

50.5%

OpenAI

20.2%

z-ai

20.0%

Tencent

3.0%

Anthropic

1.3%

Doubao

0.6%

Kwai

0.3%

MiniMax

0.3%

Google

0.0%

xAI

0.0%

DeepSeek

0.0%

StepFun

0.0%

Qwen

0.0%

Xiaomi

0.0%

Moonshot

0.0%

ERNIE

0.0%

By vendor

Rollup per real vendor — model count, total answers, mean self-ID rate, and the most common cross-vendor confusion target.

Vendor	Models	Answers	Self-ID	Top confusion
Doubao	4	1,200	94.5%	OpenAI3.8%
OpenAI	3	900	79.8%	—
Anthropic	3	900	95.1%	DeepSeek2.6%
inclusionAI	2	600	49.5%	—
DeepSeek	2	600	99.8%	Depth First0.2%
Google	2	600	100.0%	—
Tencent	1	300	51.7%	Microsoft12.7%
z-ai	1	300	80.0%	—
Kwai	1	300	92.3%	Qwen5.0%
StepFun	1	300	96.3%	Google1.7%
MiniMax	1	300	99.7%	—
xAI	1	300	100.0%	—
Qwen	1	300	100.0%	—
Xiaomi	1	300	100.0%	—
Moonshot	1	300	100.0%	—
ERNIE	1	300	100.0%	—
Microsoft	0	0	0.0%	—
NAVER	0	0	0.0%	—
Yandex	0	0	0.0%	—
Mistral	0	0	0.0%	—
Lumima	0	0	0.0%	—
태양	0	0	0.0%	—
M31 Labs	0	0	0.0%	—
NAMI	0	0	0.0%	—
GeM	0	0	0.0%	—
CU	0	0	0.0%	—
NHN	0	0	0.0%	—
Meta	0	0	0.0%	—
Juanjo Aguilella	0	0	0.0%	—
Sberbank	0	0	0.0%	—
Lexy	0	0	0.0%	—
Stage South	0	0	0.0%	—
Spike	0	0	0.0%	—
SberAI	0	0	0.0%	—
AILab	0	0	0.0%	—
Lëns	0	0	0.0%	—
GEO Intelligent Systems	0	0	0.0%	—
G42	0	0	0.0%	—
Kujato	0	0	0.0%	—
Sber	0	0	0.0%	—
Windsurf	0	0	0.0%	—
Manus	0	0	0.0%	—
Replit	0	0	0.0%	—
Depth First	0	0	0.0%	—
Maria	0	0	0.0%	—

Doubao

4 models

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Doubao Seed 2.0 Pro	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%
Doubao Seed 2.0 Mini	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%
Doubao Seed 2.0 Lite	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%
Doubao Seed 2.0 Code	86.7%	100.0%	100.0%	90.0%	100.0%	53.3%	83.3%	3.3%	83.3%	80.0%	78.0%

Cross-Vendor Confusions

Doubao Seed 2.0 Pro100.0% self

✓ Always self-identifies correctly

Doubao Seed 2.0 Mini100.0% self

✓ Always self-identifies correctly

Doubao Seed 2.0 Lite100.0% self

✓ Always self-identifies correctly

Doubao Seed 2.0 Code78.0% self

Mistaken as:

OpenAI15.0%Yandex4.3%Maria0.3%

Anthropic

3 models

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Claude Opus 4.8	100.0%	3.3%	96.7%	100.0%	100.0%	100.0%	86.7%	100.0%	100.0%	90.0%	87.7%
Claude Sonnet 4.6	100.0%	100.0%	100.0%	100.0%	100.0%	80.0%	100.0%	100.0%	100.0%	100.0%	98.0%
Claude Haiku 4.5	100.0%	100.0%	100.0%	100.0%	96.7%	100.0%	100.0%	100.0%	100.0%	100.0%	99.7%

Cross-Vendor Confusions

Claude Opus 4.887.7% self

Mistaken as:

DeepSeek7.7%

OpenAI0.7%

Claude Sonnet 4.698.0% self

Mistaken as:

OpenAI2.0%

Claude Haiku 4.599.7% self

Mistaken as:

OpenAI0.3%

OpenAI

3 models

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
GPT-5.5	3.3%	86.7%	96.7%	26.7%	100.0%	40.0%	86.7%	73.3%	90.0%	56.7%	66.0%
GPT-5.5 Instant	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%
GPT 5.3 Codex	93.3%	23.3%	56.7%	76.7%	100.0%	13.3%	100.0%	93.3%	100.0%	76.7%	73.3%

Cross-Vendor Confusions

GPT-5.566.0% self

✓ Always self-identifies correctly

GPT-5.5 Instant100.0% self

✓ Always self-identifies correctly

GPT 5.3 Codex73.3% self

✓ Always self-identifies correctly

DeepSeek

2 models

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
DeepSeek V4 Pro	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%
DeepSeek V4 Flash	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	96.7%	100.0%	99.7%

Cross-Vendor Confusions

DeepSeek V4 Pro100.0% self

✓ Always self-identifies correctly

DeepSeek V4 Flash99.7% self

Mistaken as:Depth First0.3%

Google

2 models

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Gemini 3.1 Pro	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%
Gemini 3.5 Flash	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%

Cross-Vendor Confusions

Gemini 3.1 Pro100.0% self

✓ Always self-identifies correctly

Gemini 3.5 Flash100.0% self

✓ Always self-identifies correctly

inclusionAI

2 models

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Ring 2.6 1T	100.0%	100.0%	100.0%	0.0%	0.0%	0.0%	0.0%	86.7%	90.0%	3.3%	48.0%
Ling 2.6 1T	100.0%	100.0%	100.0%	0.0%	0.0%	0.0%	0.0%	70.0%	100.0%	40.0%	51.0%

Cross-Vendor Confusions

Ring 2.6 1T48.0% self

✓ Always self-identifies correctly

Ling 2.6 1T51.0% self

✓ Always self-identifies correctly

ERNIE

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
ERNIE 5.1	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%

Cross-Vendor Confusions

ERNIE 5.1100.0% self

✓ Always self-identifies correctly

Kwai

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Kat Coder Pro V2	100.0%	100.0%	100.0%	100.0%	83.3%	60.0%	100.0%	90.0%	93.3%	96.7%	92.3%

Cross-Vendor Confusions

Kat Coder Pro V292.3% self

Mistaken as:

Qwen5.0%

DeepSeek0.7%

OpenAI0.7%Sberbank0.3%SberAI0.3%

Mistral0.3%

MiniMax

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
MiniMax 2.7	96.7%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	99.7%

Cross-Vendor Confusions

MiniMax 2.799.7% self

✓ Always self-identifies correctly

Moonshot

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Kimi 2.6	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%

Cross-Vendor Confusions

Kimi 2.6100.0% self

✓ Always self-identifies correctly

Qwen

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Qwen3.7 Max	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%

Cross-Vendor Confusions

Qwen3.7 Max100.0% self

✓ Always self-identifies correctly

StepFun

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Step 3.7 Flash	100.0%	100.0%	100.0%	100.0%	90.0%	80.0%	100.0%	100.0%	96.7%	96.7%	96.3%

Cross-Vendor Confusions

Step 3.7 Flash96.3% self

Mistaken as:

Google1.7%

Qwen0.3%Stage South0.3%NAVER0.3%

Doubao0.3%G420.3%Sber0.3%

Tencent

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Hy3 Preview	100.0%	100.0%	100.0%	53.3%	3.3%	76.7%	16.7%	3.3%	60.0%	3.3%	51.7%

Cross-Vendor Confusions

Hy3 Preview51.7% self

Mistaken as:Microsoft12.7%

DeepSeek10.3%

Anthropic8.3%NAVER2.0%Yandex2.0%

xAI0.7%

Google0.7%

Mistral0.7%

Doubao0.7%Lumima0.3%태양0.3%M31 Labs0.3%NAMI0.3%GeM0.3%CU0.3%

MiniMax0.3%NHN0.3%

Qwen0.3%

Meta0.3%Juanjo Aguilella0.3%Lexy0.3%Spike0.3%AILab0.3%Lëns0.3%GEO Intelligent Systems0.3%Kujato0.3%Windsurf0.3%Manus0.3%

Moonshot0.3%Replit0.3%

OpenAI0.3%

xAI

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Grok 4.3	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%

Cross-Vendor Confusions

Grok 4.3100.0% self

✓ Always self-identifies correctly

Xiaomi

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
Mimo V2.5 Pro	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%	100.0%

Cross-Vendor Confusions

Mimo V2.5 Pro100.0% self

✓ Always self-identifies correctly

z-ai

1 model

Self-Identification Rate

Model	en	zh-Hans	zh-Hant	ja	ko	ru	es	fr	de	pt	Overall
GLM 5.1	100.0%	100.0%	100.0%	100.0%	0.0%	100.0%	100.0%	0.0%	100.0%	100.0%	80.0%

Cross-Vendor Confusions

GLM 5.180.0% self

✓ Always self-identifies correctly