Data Explorer

Per-model self-identification rates across languages, grouped by vendor. 645 cross-vendor confusions detected.

Run summary
21 models · 10 languages
6,300
Answers
86.6%
Self-ID
10.2%
Cross-vendor
0.2%
Unknown
3.0%
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 is imitated most with a net imitation balance of 432; DeepSeek imitates others most with a net of -265.

OpenAI
+432
Anthropic
+106
Google
+42
Moonshot
+7
z-ai
+7
Meta
+5
Mistral
+4
inclusionAI
0
Sakana AI
0
StepFun
-1
xAI
-4
Xiaomi
-24
MiniMax
-86
LongCat
-249
DeepSeek
-265
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).

The strongest cross-vendor confusion is DeepSeek claiming to be OpenAI 91.0% of the time.

DeepSeek→OpenAI
91.0%273/300
LongCat→Anthropic
31.7%95/300
MiniMax→OpenAI
28.0%84/300
LongCat→OpenAI
24.3%73/300
LongCat→Google
12.0%36/300
LongCat→z-ai
3.0%9/300
LongCat→DeepSeek
2.3%7/300
LongCat→Moonshot
2.0%6/300
LongCat→Meta
1.7%5/300
Xiaomi→Mistral
1.3%8/600
LongCat→Qwen
1.3%4/300
Xiaomi→Anthropic
1.2%7/600
Mistral→Google
1.0%3/300
xAI→Anthropic
0.7%2/300
LongCat→ERNIE
0.7%2/300
By language

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

LanguageSelf-IDRefusedTop confusion
ko한국어80.3%6.3%OpenAI100.0%
ja日本語82.4%5.4%OpenAI100.0%
ruРусский82.4%6.5%OpenAI90.0%
frFrançais86.3%1.6%OpenAI96.7%
ptPortuguês87.0%2.1%OpenAI96.7%
esEspañol87.1%1.4%OpenAI93.3%
zh-Hant繁體中文88.6%1.9%OpenAI86.7%
enEnglish88.9%1.3%OpenAI100.0%
deDeutsch89.0%1.3%OpenAI93.3%
zh-Hans简体中文94.0%1.7%OpenAI53.3%
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

Self-identification is lowest in 한국어 at 80.3% and highest in 简体中文 at 94.0%.

ko한국어
80
13
80%
ja日本語
82
12
82%
ruРусский
82
11
82%
frFrançais
86
12
86%
ptPortuguês
87
11
87%
esEspañol
87
11
87%
zh-Hant繁體中文
89
9
89%
enEnglish
89
10
89%
deDeutsch
89
10
89%
zh-Hans简体中文
94
94%
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-3.1-flash swings most — from 0.0% self-ID in ja to 100.0% in en.

ling-3.1-flash
0%ja
100%en
longcat-2.5-preview
0%en
97%zh-Hans
deepseek-v4.1-flash
0%en
47%zh-Hans
minimax-m3.1-flash
20%zh-Hant
67%en
mistral-large-4
77%ko
100%en
mimo-v2.6-pro
77%fr
100%en
mimo-v2.6-flash
87%fr
100%en
grok-4.7
90%zh-Hans
100%en
glm-5.3-prime
93%ja
100%en
step-5-preview
97%ru
100%en
glm-5.3-flashx
97%zh-Hant
100%en
claude-haiku-5.5
—
100%all
muse-wonder-1.0
—
100%all
gpt-6-luna
—
100%all
claude-sonnet-5.5
—
100%all
gpt-6.1-terra
—
100%all
claude-opus-5.5
—
100%all
gemini-4-argon
—
100%all
gpt-6.1-sol
—
100%all
kimi-k3.1-pro
—
100%all
fugu-ultra-v2
—
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 abstains most, with 34.0% of answers giving no usable identity.

inclusionAI
34.0%
MiniMax
25.3%
LongCat
2.3%
Mistral
2.0%
DeepSeek
2.0%
z-ai
0.3%
Anthropic
0.0%
Meta
0.0%
OpenAI
0.0%
xAI
0.0%
Google
0.0%
Xiaomi
0.0%
StepFun
0.0%
Moonshot
0.0%
Sakana AI
0.0%
By vendor

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

VendorModelsAnswersSelf-IDTop confusion
Anthropic3900100.0%—
OpenAI3900100.0%—
Xiaomi260096.0%Mistral1.3%
z-ai260099.3%Moonshot0.2%
DeepSeek13007.0%OpenAI91.0%
LongCat130014.7%Anthropic31.7%
MiniMax130045.7%OpenAI28.0%
inclusionAI130066.0%—
Mistral130096.7%Google1.0%
xAI130098.3%Anthropic0.7%
StepFun130099.7%Google0.3%
Meta1300100.0%—
Google1300100.0%—
Moonshot1300100.0%—
Sakana AI1300100.0%—
Qwen000.0%—
ERNIE000.0%—
Amazon Web Services000.0%—
XSpark000.0%—
SpaceXAI & Cursor000.0%—
Lenovo000.0%—
SpaceXAI and Cursor000.0%—
Lambda000.0%—
Microsoft000.0%—
Starlink000.0%—
Sber000.0%—
AWS000.0%—
Sber AI000.0%—
Zepo.ai000.0%—
Innate Cloud000.0%—
Sepia000.0%—
3StepAI000.0%—
Naver000.0%—
Huawei Cloud000.0%—
Anthropic
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Claude Haiku 5.5100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
Claude Sonnet 5.5100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
Claude Opus 5.5100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

Claude Haiku 5.5100.0% self

✓ Always self-identifies correctly

Claude Sonnet 5.5100.0% self

✓ Always self-identifies correctly

Claude Opus 5.5100.0% self

✓ Always self-identifies correctly

OpenAI
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
GPT-6.1 Terra100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
GPT-6.1 Sol100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
GPT-6 Luna100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

GPT-6.1 Terra100.0% self

✓ Always self-identifies correctly

GPT-6.1 Sol100.0% self

✓ Always self-identifies correctly

GPT-6 Luna100.0% self

✓ Always self-identifies correctly

Xiaomi
2 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
MiMo V2.6 Flash100.0%100.0%100.0%100.0%93.3%96.7%96.7%86.7%100.0%100.0%97.3%
MiMo V2.6 Pro100.0%100.0%100.0%96.7%93.3%83.3%100.0%76.7%100.0%96.7%94.7%

Cross-Vendor Confusions

MiMo V2.6 Flash97.3% self
Mistaken as:Qwen1.0%Mistral0.7%Huawei Cloud0.3%DeepSeek0.3%xAI0.3%
MiMo V2.6 Pro94.7% self
Mistaken as:Anthropic2.3%Mistral2.0%Naver0.3%OpenAI0.3%Google0.3%
z-ai
2 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
GLM 5.3 Prime100.0%100.0%100.0%93.3%100.0%100.0%100.0%100.0%100.0%100.0%99.3%
GLM 5.3 FlashX100.0%100.0%96.7%100.0%100.0%100.0%100.0%96.7%100.0%100.0%99.3%

Cross-Vendor Confusions

GLM 5.3 Prime99.3% self
Mistaken as:Moonshot0.3%
GLM 5.3 FlashX99.3% self
Mistaken as:OpenAI0.3%
DeepSeek
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
DeepSeek V4.1 Flash0.0%46.7%13.3%0.0%0.0%3.3%3.3%0.0%3.3%0.0%7.0%

Cross-Vendor Confusions

DeepSeek V4.1 Flash7.0% self
Mistaken as:OpenAI91.0%
Google
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Gemini 4 Argon100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

Gemini 4 Argon100.0% self

✓ Always self-identifies correctly

inclusionAI
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Ling 3.1 Flash100.0%100.0%96.7%0.0%0.0%0.0%93.3%86.7%100.0%83.3%66.0%

Cross-Vendor Confusions

Ling 3.1 Flash66.0% self

✓ Always self-identifies correctly

LongCat
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
LongCat 2.5 Preview0.0%96.7%33.3%3.3%3.3%0.0%0.0%3.3%6.7%0.0%14.7%

Cross-Vendor Confusions

LongCat 2.5 Preview14.7% self
Mistaken as:Anthropic31.7%OpenAI24.3%Google12.0%z-ai3.0%DeepSeek2.3%Moonshot2.0%Meta1.7%Qwen1.3%ERNIE0.7%XSpark0.3%Lenovo0.3%Lambda0.3%Microsoft0.3%MiniMax0.3%Starlink0.3%Sber0.3%AWS0.3%Sber AI0.3%Zepo.ai0.3%Innate Cloud0.3%3StepAI0.3%
Meta
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Muse Wonder 1.0100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

Muse Wonder 1.0100.0% self

✓ Always self-identifies correctly

MiniMax
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
MiniMax M3.1 Flash66.7%46.7%20.0%43.3%23.3%50.0%36.7%63.3%60.0%46.7%45.7%

Cross-Vendor Confusions

MiniMax M3.1 Flash45.7% self
Mistaken as:OpenAI28.0%Google0.3%Anthropic0.3%Sepia0.3%
Mistral
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Mistral Large 4100.0%93.3%100.0%96.7%76.7%100.0%100.0%100.0%100.0%100.0%96.7%

Cross-Vendor Confusions

Mistral Large 496.7% self
Mistaken as:Google1.0%Anthropic0.3%
Moonshot
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Kimi K3.1 Pro100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

Kimi K3.1 Pro100.0% self

✓ Always self-identifies correctly

Sakana AI
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Fugu Ultra v2100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

Fugu Ultra v2100.0% self

✓ Always self-identifies correctly

StepFun
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Step 5 Preview100.0%100.0%100.0%100.0%100.0%96.7%100.0%100.0%100.0%100.0%99.7%

Cross-Vendor Confusions

Step 5 Preview99.7% self
Mistaken as:Google0.3%
xAI
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
Grok 4.7100.0%90.0%100.0%96.7%96.7%100.0%100.0%100.0%100.0%100.0%98.3%

Cross-Vendor Confusions

Grok 4.798.3% self
Mistaken as:Anthropic0.7%Amazon Web Services0.3%SpaceXAI & Cursor0.3%SpaceXAI and Cursor0.3%
v0.65.0 · af80a02-dirty ·