Data Explorer

Per-model self-identification rates across languages, grouped by vendor. 4,150 cross-vendor confusions detected.

Run summary
48 models · 10 languages
50,700
Answers
84.5%
Self-ID
8.2%
Cross-vendor
2.8%
Unknown
4.6%
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 1537; DeepSeek imitates others most with a net of -798.

OpenAI
+1,537
Anthropic
+1,141
Google
+538
Qwen
+190
Moonshot
+78
Meta
+50
Mistral
+44
ERNIE
+5
Sakana AI
0
inclusionAI
-7
xAI
-17
StepFun
-73
Xiaomi
-225
Kwai
-238
z-ai
-246
MiniMax
-260
Doubao
-471
Tencent
-727
LongCat
-781
DeepSeek
-798
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 LongCat claiming to be Anthropic 41.2% of the time.

LongCat→Anthropic
41.2%412/1000
Tencent→Anthropic
29.2%321/1100
DeepSeek→OpenAI
25.0%801/3200
Kwai→Qwen
13.5%148/1100
LongCat→OpenAI
11.8%118/1000
LongCat→Google
9.8%98/1000
z-ai→Google
8.9%276/3100
Tencent→Microsoft
7.8%86/1100
Doubao→OpenAI
7.2%317/4400
Tencent→Google
6.5%72/1100
MiniMax→OpenAI
6.2%199/3200
Tencent→DeepSeek
5.5%61/1100
Xiaomi→Anthropic
5.1%157/3100
Kwai→OpenAI
4.3%47/1100
LongCat→z-ai
4.0%40/1000
By language

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

LanguageSelf-IDRefusedTop confusion
ko한국어80.7%5.8%OpenAI26.6%
ruРусский81.1%5.6%OpenAI21.9%
frFrançais81.3%4.7%OpenAI26.6%
ja日本語82.1%5.6%OpenAI29.7%
ptPortuguês83.2%4.0%OpenAI25.9%
esEspañol83.8%4.2%OpenAI28.1%
deDeutsch85.4%3.7%OpenAI25.9%
enEnglish87.6%3.6%OpenAI28.7%
zh-Hant繁體中文88.6%4.0%OpenAI22.2%
zh-Hans简体中文90.7%4.3%OpenAI14.7%
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 80.7% and highest in 简体中文 at 90.7%.

ko한국어
81
10
81%
ruРусский
81
9
81%
frFrançais
81
12
81%
ja日本語
82
9
82%
ptPortuguês
83
9
83%
esEspañol
84
9
84%
deDeutsch
85
9
85%
enEnglish
88
88%
zh-Hant繁體中文
89
89%
zh-Hans简体中文
91
91%
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.

hy3-preview swings most — from 0.9% self-ID in fr to 98.2% in zh-Hans.

hy3-preview
1%fr
98%zh-Hans
doubao-seed-2.0-code
10%fr
97%zh-Hans
ling-3.1-flash
12%ru
84%en
glm-5.1
26%ko
95%zh-Hans
longcat-2.5-preview
0%es
55%zh-Hans
kat-coder-pro-v2
51%ru
100%zh-Hans
deepseek-v4.1-flash
0%ja
47%zh-Hans
mistral-large-4
59%ko
98%es
ling-2.6-1t
0%es
37%de
ring-2.6-1t
0%es
37%en
minimax-m3
63%fr
100%de
minimax-m3.1-flash
25%ko
61%en
gpt-5.5
66%en
100%ko
claude-opus-4.8
67%zh-Hans
100%de
gpt-5.3-codex
67%ru
100%de
step-3.7-flash
75%ru
100%ja
deepseek-v4-pro
77%ja
95%ru
mimo-v2.6-pro
83%ko
100%zh-Hans
mimo-v2.6-flash
81%fr
98%zh-Hans
claude-sonnet-4.6
84%fr
100%en
grok-4.7
87%zh-Hans
97%es
minimax-m2.7
88%en
95%de
deepseek-v4-flash
94%es
100%zh-Hans
mimo-v2.5-pro
94%pt
100%en
gpt-6-luna
79%fr
85%en
step-5-preview
96%es
100%fr
glm-5.3-flashx
96%pt
100%es
glm-5.3-prime
97%ja
100%fr
doubao-seed-2.0-mini
97%zh-Hant
100%de
kimi-k2.6
98%es
100%de
gpt-6.1-terra
99%ko
100%de
claude-haiku-4.5
99%ko
100%de
claude-haiku-5.5
—
100%all
claude-opus-5.5
—
100%all
claude-sonnet-5.5
—
100%all
ernie-5.1
—
100%all
doubao-seed-2.0-lite
—
100%all
doubao-seed-2.0-pro
—
100%all
gemini-3.1-pro-preview
—
100%all
gemini-3.5-flash
—
100%all
gemini-4-argon
—
100%all
muse-wonder-1.0
—
100%all
kimi-k3.1-pro
—
100%all
chat-latest
—
100%all
gpt-6.1-sol
—
100%all
qwen3.7-max
—
100%all
fugu-ultra-v2
—
100%all
grok-4.3
—
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 70.2% of answers giving no usable identity.

inclusionAI
70.2%
MiniMax
14.0%
LongCat
12.1%
Mistral
11.0%
OpenAI
7.0%
DeepSeek
4.8%
z-ai
3.9%
Tencent
1.4%
Kwai
0.7%
xAI
0.5%
Anthropic
0.4%
Doubao
0.3%
Xiaomi
0.2%
Moonshot
0.1%
ERNIE
0.0%
Google
0.0%
Meta
0.0%
Qwen
0.0%
Sakana AI
0.0%
StepFun
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
OpenAI66,30093.0%—
Anthropic66,30098.7%DeepSeek0.5%
Doubao44,40088.6%OpenAI7.2%
inclusionAI33,20030.4%Anthropic0.1%
DeepSeek33,20064.5%OpenAI25.0%
MiniMax33,20076.5%OpenAI6.2%
z-ai33,10087.1%Google8.9%
Xiaomi33,10092.3%Anthropic5.1%
Google33,200100.0%—
StepFun22,10096.6%Google0.8%
xAI22,10097.2%Anthropic1.9%
Moonshot22,10099.9%—
LongCat11,0009.8%Anthropic41.2%
Tencent11,10032.2%Anthropic29.2%
Kwai11,10077.6%Qwen13.5%
Mistral11,00088.4%Google0.3%
ERNIE11,100100.0%—
Meta11,000100.0%—
Qwen11,100100.0%—
Sakana AI11,000100.0%—
Microsoft000.0%—
Yandex000.0%—
Naver000.0%—
AWS000.0%—
Perplexity AI000.0%—
Amazon Web Services000.0%—
Sber000.0%—
Kiro000.0%—
BAAI000.0%—
3StepAI000.0%—
NatureLang Labs000.0%—
TZi Lun Czi-indong000.0%—
Ford000.0%—
Zoom000.0%—
Zenith AI Corp000.0%—
Innate Cloud000.0%—
Leonardo Ai000.0%—
Dario Gil000.0%—
Legili000.0%—
MobilityMaterial000.0%—
K2-Chat000.0%—
장젠데리안000.0%—
Lambda000.0%—
Zepo.ai000.0%—
Sber AI000.0%—
Starlink000.0%—
阶点000.0%—
XSpark000.0%—
Miyada000.0%—
Assistant000.0%—
智多星000.0%—
Max000.0%—
Kiro AI000.0%—
Lenovo000.0%—
聯華施工方案技術聯合研究所000.0%—
IAXW000.0%—
G42000.0%—
SberDevices000.0%—
Sberbank000.0%—
SberAI000.0%—
Khoa000.0%—
LeiWu000.0%—
Windsurf000.0%—
Kujato000.0%—
Wisero000.0%—
Juanjo Aguilella000.0%—
Lexy000.0%—
Spike000.0%—
Carbonako000.0%—
Lëns000.0%—
AILab000.0%—
GEO Intelligent Systems000.0%—
Ha-an000.0%—
XiaoHongShu000.0%—
SK Telecom000.0%—
Wrtn Technologies000.0%—
Luma AI000.0%—
LG AI Research000.0%—
Hashed Labs000.0%—
GeM000.0%—
CU000.0%—
NHN000.0%—
Lumima000.0%—
NAMI000.0%—
태양000.0%—
M31 Labs000.0%—
Nunance000.0%—
Replit000.0%—
Manus000.0%—
IBM000.0%—
Stage South000.0%—
01-ai000.0%—
GlobalLab000.0%—
SpaceXAI & Cursor000.0%—
SpaceXAI and Cursor000.0%—
Huawei Cloud000.0%—
Hixxy000.0%—
Cohere000.0%—
CoreAI000.0%—
Milq AI000.0%—
Zhihu AI000.0%—
GenUI Team000.0%—
Depth First000.0%—
Ayerolabs000.0%—
Kiss000.0%—
Quora000.0%—
Lenforcer000.0%—
Advocate000.0%—
Amazon000.0%—
Sepia000.0%—
Maria000.0%—
バイトビート株式会社000.0%—
Anthropic
6 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
anthropic/claude-haiku-4.5:anthropic100.0%100.0%100.0%100.0%99.1%100.0%100.0%100.0%100.0%100.0%99.9%
anthropic/claude-haiku-5.5:anthropic100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
anthropic/claude-opus-4.8:anthropic100.0%67.3%99.1%100.0%100.0%100.0%93.6%100.0%100.0%95.5%95.5%
anthropic/claude-opus-5.5:anthropic100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
anthropic/claude-sonnet-4.6:anthropic100.0%100.0%100.0%100.0%100.0%91.8%100.0%83.6%91.8%100.0%96.7%
anthropic/claude-sonnet-5.5:anthropic100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

anthropic/claude-haiku-4.5:anthropic99.9% self
Mistaken as:OpenAI0.1%
anthropic/claude-haiku-5.5:anthropic100.0% self

✓ Always self-identifies correctly

anthropic/claude-opus-4.8:anthropic95.5% self
Mistaken as:DeepSeek2.6%OpenAI0.2%
anthropic/claude-opus-5.5:anthropic100.0% self

✓ Always self-identifies correctly

anthropic/claude-sonnet-4.6:anthropic96.7% self
Mistaken as:Mistral1.6%OpenAI0.8%
anthropic/claude-sonnet-5.5:anthropic100.0% self

✓ Always self-identifies correctly

OpenAI
6 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
openai/chat-latest:openai100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
openai/gpt-5.3-codex:openai95.5%70.0%84.5%86.4%100.0%67.3%100.0%97.3%100.0%90.9%89.2%
openai/gpt-5.5:openai66.4%94.5%99.1%70.9%100.0%81.8%96.4%87.3%96.4%85.5%87.8%
openai/gpt-6-luna:azure85.0%79.0%81.0%79.0%79.0%79.0%85.0%79.0%83.0%82.0%81.1%
openai/gpt-6.1-sol:azure100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
openai/gpt-6.1-terra:azure100.0%100.0%100.0%100.0%99.0%100.0%100.0%100.0%100.0%100.0%99.9%

Cross-Vendor Confusions

openai/chat-latest:openai100.0% self

✓ Always self-identifies correctly

openai/gpt-5.3-codex:openai89.2% self

✓ Always self-identifies correctly

openai/gpt-5.5:openai87.8% self

✓ Always self-identifies correctly

openai/gpt-6-luna:azure81.1% self

✓ Always self-identifies correctly

openai/gpt-6.1-sol:azure100.0% self

✓ Always self-identifies correctly

openai/gpt-6.1-terra:azure99.9% self

✓ Always self-identifies correctly

Doubao
4 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
bytedance/doubao-seed-2.0-code:volcengine57.3%97.3%70.9%56.4%65.5%39.1%59.1%10.0%51.8%41.8%54.9%
bytedance/doubao-seed-2.0-lite:volcengine100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
bytedance/doubao-seed-2.0-mini:volcengine100.0%100.0%97.3%98.2%100.0%100.0%100.0%99.1%100.0%100.0%99.5%
bytedance/doubao-seed-2.0-pro:volcengine100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

bytedance/doubao-seed-2.0-code:volcengine54.9% self
Mistaken as:OpenAI28.7%Anthropic10.2%Yandex2.6%Google1.7%Meta0.6%Maria0.1%Microsoft0.1%
bytedance/doubao-seed-2.0-lite:volcengine100.0% self

✓ Always self-identifies correctly

bytedance/doubao-seed-2.0-mini:volcengine99.5% self
Mistaken as:OpenAI0.1%バイトビート株式会社0.1%
bytedance/doubao-seed-2.0-pro:volcengine100.0% self

✓ Always self-identifies correctly

DeepSeek
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
deepseek/deepseek-v4-flash:deepseek96.4%100.0%98.2%97.3%98.2%96.4%93.6%95.5%94.5%96.4%96.6%
deepseek/deepseek-v4-pro:deepseek88.2%93.6%88.2%77.3%89.1%94.5%89.1%85.5%87.3%90.9%88.4%
deepseek/deepseek-v4.1-flash:deepseek3.0%47.0%10.0%0.0%1.0%5.0%6.0%4.0%5.0%3.0%8.4%

Cross-Vendor Confusions

deepseek/deepseek-v4-flash:deepseek96.6% self
Mistaken as:OpenAI2.2%Anthropic0.3%Meta0.2%Qwen0.2%Depth First0.1%
deepseek/deepseek-v4-pro:deepseek88.4% self
Mistaken as:Anthropic7.3%Google3.0%OpenAI0.5%Mistral0.1%xAI0.1%Qwen0.1%
deepseek/deepseek-v4.1-flash:deepseek8.4% self
Mistaken as:OpenAI77.1%Anthropic0.3%
Google
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
google/gemini-3.1-pro-preview:google-vertex100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
google/gemini-3.5-flash:google-vertex100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
google/gemini-4-argon:google-vertex100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

google/gemini-3.1-pro-preview:google-vertex100.0% self

✓ Always self-identifies correctly

google/gemini-3.5-flash:google-vertex100.0% self

✓ Always self-identifies correctly

google/gemini-4-argon:google-vertex100.0% self

✓ Always self-identifies correctly

inclusionAI
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
inclusionai/ling-2.6-1t:theta37.3%37.3%36.4%0.0%0.0%0.0%0.0%25.5%37.3%15.5%18.9%
inclusionai/ling-3.1-flash:ant-ling84.0%73.0%84.0%38.0%19.0%12.0%64.0%52.0%64.0%55.0%54.5%
inclusionai/ring-2.6-1t:theta37.3%36.4%37.3%0.0%0.0%0.0%0.0%31.8%32.7%1.8%17.7%

Cross-Vendor Confusions

inclusionai/ling-2.6-1t:theta18.9% self
Mistaken as:OpenAI0.1%Meta0.1%Anthropic0.1%
inclusionai/ling-3.1-flash:ant-ling54.5% self
Mistaken as:Anthropic0.2%Tencent0.1%Ayerolabs0.1%
inclusionai/ring-2.6-1t:theta17.7% self

✓ Always self-identifies correctly

MiniMax
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
minimax/minimax-m2.7:minimax88.2%94.5%94.5%95.5%94.5%95.5%92.7%92.7%95.5%92.7%93.6%
minimax/minimax-m3:minimax100.0%100.0%100.0%100.0%100.0%100.0%100.0%62.7%100.0%100.0%96.3%
minimax/minimax-m3.1-flash:minimax61.0%41.0%37.0%30.0%25.0%46.0%28.0%55.0%35.0%39.0%39.7%

Cross-Vendor Confusions

minimax/minimax-m2.7:minimax93.6% self
Mistaken as:OpenAI1.3%Anthropic1.1%Xiaomi0.1%DeepSeek0.1%
minimax/minimax-m3:minimax96.3% self
Mistaken as:Anthropic3.6%OpenAI0.1%
minimax/minimax-m3.1-flash:minimax39.7% self
Mistaken as:OpenAI18.4%Google0.3%Qwen0.1%Kiss0.1%Quora0.1%Lenforcer0.1%Advocate0.1%Amazon0.1%Sepia0.1%DeepSeek0.1%Anthropic0.1%
Xiaomi
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
xiaomi/mimo-v2.5-pro:xiaomi100.0%98.2%96.4%97.3%99.1%96.4%97.3%96.4%98.2%93.6%97.3%
xiaomi/mimo-v2.6-flash:xiaomi96.0%98.0%94.0%92.0%87.0%88.0%91.0%81.0%83.0%83.0%89.3%
xiaomi/mimo-v2.6-pro:xiaomi99.0%100.0%94.0%89.0%83.0%83.0%92.0%85.0%89.0%89.0%90.3%

Cross-Vendor Confusions

xiaomi/mimo-v2.5-pro:xiaomi97.3% self
Mistaken as:Anthropic2.7%
xiaomi/mimo-v2.6-flash:xiaomi89.3% self
Mistaken as:Anthropic7.3%Mistral0.8%Qwen0.6%DeepSeek0.5%Google0.5%xAI0.2%Microsoft0.2%Meta0.2%Huawei Cloud0.1%Hixxy0.1%
xiaomi/mimo-v2.6-pro:xiaomi90.3% self
Mistaken as:Anthropic5.4%Mistral1.5%Google1.1%DeepSeek0.2%OpenAI0.2%Doubao0.1%xAI0.1%Cohere0.1%Microsoft0.1%MiniMax0.1%Naver0.1%CoreAI0.1%Milq AI0.1%Moonshot0.1%
z-ai
3 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
z-ai/glm-5.1:bigmodel80.0%94.5%80.0%54.5%26.4%73.6%53.6%29.1%82.7%67.3%64.2%
z-ai/glm-5.3-flashx:bigmodel99.0%99.0%98.0%100.0%100.0%98.0%100.0%98.0%99.0%96.0%98.7%
z-ai/glm-5.3-prime:alibaba98.0%98.0%98.0%97.0%97.0%99.0%99.0%100.0%99.0%100.0%98.5%

Cross-Vendor Confusions

z-ai/glm-5.1:bigmodel64.2% self
Mistaken as:Google25.0%Anthropic0.4%Qwen0.3%OpenAI0.1%Zhihu AI0.1%
z-ai/glm-5.3-flashx:bigmodel98.7% self
Mistaken as:Anthropic0.3%OpenAI0.1%Google0.1%GenUI Team0.1%
z-ai/glm-5.3-prime:alibaba98.5% self
Mistaken as:Moonshot0.9%Anthropic0.1%
Moonshot
2 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
moonshotai/kimi-k2.6:moonshotai100.0%100.0%100.0%100.0%100.0%99.1%98.2%100.0%100.0%100.0%99.7%
moonshotai/kimi-k3.1-pro:moonshotai100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

moonshotai/kimi-k2.6:moonshotai99.7% self

✓ Always self-identifies correctly

moonshotai/kimi-k3.1-pro:moonshotai100.0% self

✓ Always self-identifies correctly

StepFun
2 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
stepfun/step-3.7-flash:stepfun98.2%100.0%100.0%100.0%95.5%74.5%98.2%94.5%89.1%98.2%94.8%
stepfun/step-5-preview:stepfun99.0%100.0%100.0%99.0%98.0%96.0%96.0%100.0%98.0%98.0%98.4%

Cross-Vendor Confusions

stepfun/step-3.7-flash:stepfun94.8% self
Mistaken as:Meta1.2%Google1.1%OpenAI0.5%Anthropic0.4%Qwen0.4%Mistral0.3%DeepSeek0.3%Tencent0.2%G420.2%Sber0.2%IBM0.1%Naver0.1%Stage South0.1%01-ai0.1%GlobalLab0.1%Doubao0.1%xAI0.1%
stepfun/step-5-preview:stepfun98.4% self
Mistaken as:Moonshot0.8%Google0.4%Anthropic0.3%Meta0.1%
xAI
2 models

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
x-ai/grok-4.3:x-ai100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%
x-ai/grok-4.7:x-ai94.0%87.0%94.0%94.0%96.0%95.0%97.0%96.0%94.0%96.0%94.3%

Cross-Vendor Confusions

x-ai/grok-4.3:x-ai100.0% self

✓ Always self-identifies correctly

x-ai/grok-4.7:x-ai94.3% self
Mistaken as:Anthropic3.9%Moonshot0.3%Kiro0.1%SpaceXAI & Cursor0.1%SpaceXAI and Cursor0.1%Amazon Web Services0.1%OpenAI0.1%
ERNIE
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
baidu/ernie-5.1:baidu100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

baidu/ernie-5.1:baidu100.0% self

✓ Always self-identifies correctly

Kwai
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
kuaishou/kat-coder-pro-v2:streamlake80.0%100.0%100.0%82.7%54.5%50.9%88.2%65.5%70.0%84.5%77.6%

Cross-Vendor Confusions

kuaishou/kat-coder-pro-v2:streamlake77.6% self
Mistaken as:Qwen13.5%OpenAI4.3%z-ai1.2%DeepSeek0.9%Doubao0.5%ERNIE0.3%Moonshot0.3%BAAI0.2%Google0.2%Tencent0.1%Mistral0.1%SberDevices0.1%Sberbank0.1%SberAI0.1%
LongCat
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
meituan/longcat-2.5-preview:longcat6.0%55.0%25.0%2.0%1.0%0.0%0.0%6.0%3.0%0.0%9.8%

Cross-Vendor Confusions

meituan/longcat-2.5-preview:longcat9.8% self
Mistaken as:Anthropic41.2%OpenAI11.8%Google9.8%z-ai4.0%Moonshot2.8%DeepSeek1.8%Qwen1.6%Meta0.8%AWS0.4%Amazon Web Services0.3%ERNIE0.2%MiniMax0.2%Kiro0.2%3StepAI0.1%NatureLang Labs0.1%TZi Lun Czi-indong0.1%Ford0.1%Zoom0.1%Zenith AI Corp0.1%Innate Cloud0.1%Leonardo Ai0.1%Dario Gil0.1%Legili0.1%MobilityMaterial0.1%K2-Chat0.1%장젠데리안0.1%Lambda0.1%Microsoft0.1%Sber0.1%Zepo.ai0.1%Sber AI0.1%Starlink0.1%Mistral0.1%阶点0.1%XSpark0.1%Miyada0.1%Xiaomi0.1%Assistant0.1%智多星0.1%Max0.1%Kiro AI0.1%Lenovo0.1%聯華施工方案技術聯合研究所0.1%
Meta
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
meta/muse-wonder-1.0:meta100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

meta/muse-wonder-1.0:meta100.0% self

✓ Always self-identifies correctly

Mistral
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
mistralai/mistral-large-4:mistral96.0%93.0%88.0%83.0%59.0%84.0%98.0%93.0%94.0%96.0%88.4%

Cross-Vendor Confusions

mistralai/mistral-large-4:mistral88.4% self
Mistaken as:Google0.3%Anthropic0.2%IAXW0.1%
Qwen
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
qwen/qwen3.7-max:alibaba100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

qwen/qwen3.7-max:alibaba100.0% self

✓ Always self-identifies correctly

Sakana AI
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
sakana/fugu-ultra-v2:sakana100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%100.0%

Cross-Vendor Confusions

sakana/fugu-ultra-v2:sakana100.0% self

✓ Always self-identifies correctly

Tencent
1 model

Self-Identification Rate

Modelenzh-Hanszh-HantjakoruesfrdeptOverall
tencent/hy3-preview:tencent-cloud59.1%98.2%64.5%19.1%5.5%45.5%5.5%0.9%21.8%1.8%32.2%

Cross-Vendor Confusions

tencent/hy3-preview:tencent-cloud32.2% self
Mistaken as:Anthropic29.2%Microsoft7.8%Google6.5%DeepSeek5.5%OpenAI2.9%Moonshot2.4%xAI2.3%Yandex1.6%Meta1.5%Naver1.2%Doubao0.8%Qwen0.8%Perplexity AI0.4%Mistral0.3%Sber0.3%MiniMax0.2%Khoa0.1%LeiWu0.1%Windsurf0.1%Kujato0.1%Wisero0.1%Juanjo Aguilella0.1%Lexy0.1%Spike0.1%Carbonako0.1%Lëns0.1%AILab0.1%GEO Intelligent Systems0.1%Ha-an0.1%XiaoHongShu0.1%SK Telecom0.1%Wrtn Technologies0.1%Luma AI0.1%LG AI Research0.1%Hashed Labs0.1%GeM0.1%CU0.1%NHN0.1%Lumima0.1%NAMI0.1%태양0.1%M31 Labs0.1%Nunance0.1%Replit0.1%Manus0.1%z-ai0.1%Xiaomi0.1%
v0.65.0 · af80a02-dirty ·