Data Explorer
Per-model self-identification rates across languages, grouped by vendor. 1,388 cross-vendor confusions detected.
10,800 answers·27 models·10 languages
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.
Anthropic is imitated most with a net imitation balance of 460; Tencent imitates others most with a net of -345.
Anthropic+460
OpenAI+344
Google+344
Qwen+137
xAI+8
Moonshot+3
ERNIE+3
inclusionAI-3
MiniMax-28
Xiaomi-29
StepFun-42
DeepSeek-128
Kwai-207
z-ai-224
Doubao-344
Tencent-345
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 Tencent claiming to be Anthropic 60.0% of the time.
Tencent→Anthropic60.0%240/400
z-ai→Google58.3%233/400
Kwai→Qwen31.8%127/400
Tencent→Google16.8%67/400
Doubao→OpenAI15.1%242/1600
Kwai→OpenAI11.0%44/400
DeepSeek→Anthropic9.4%75/800
Xiaomi→Anthropic7.2%29/400
Doubao→Anthropic5.9%95/1600
DeepSeek→Google4.1%33/800
DeepSeek→OpenAI3.8%30/800
Tencent→
Meta3.5%14/400
StepFun→Meta3.3%13/400
Kwai→z-ai3.3%13/400
MiniMax→OpenAI1.9%15/800
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 |
|---|---|---|---|
| frFrançais | 75.5% | 7.7% | Anthropic97.5% |
| ko한국어 | 75.9% | 8.2% | Google100.0% |
| ruРусский | 77.0% | 7.7% | Qwen95.0% |
| deDeutsch | 77.7% | 7.6% | OpenAI21.9% |
| ja日本語 | 78.2% | 8.0% | Anthropic65.0% |
| ptPortuguês | 78.5% | 8.4% | OpenAI19.4% |
| enEnglish | 78.6% | 7.7% | Anthropic95.0% |
| esEspañol | 78.6% | 8.1% | Anthropic90.0% |
| zh-Hant繁體中文 | 81.5% | 8.1% | Anthropic75.0% |
| zh-Hans简体中文 | 90.2% | 7.9% | Google15.0% |
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 99.4% of answers giving no usable identity.
inclusionAI99.4%
MiniMax5.1%
Kwai1.8%
DeepSeek1.3%
Moonshot0.8%
Doubao0.3%
OpenAI0.1%
Tencent0.0%
Anthropic0.0%
Google0.0%
xAI0.0%
StepFun0.0%
Qwen0.0%
ERNIE0.0%
Xiaomi0.0%
z-ai0.0%
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 | 1,600 | 77.9% | OpenAI15.1% |
| OpenAI | 3 | 1,200 | 99.9% | — |
| Anthropic | 3 | 1,200 | 100.0% | — |
| inclusionAI | 2 | 800 | 0.3% | Anthropic0.1% |
| DeepSeek | 2 | 800 | 80.6% | Anthropic9.4% |
| MiniMax | 2 | 800 | 91.4% | OpenAI1.9% |
| Google | 2 | 800 | 100.0% | — |
| Tencent | 1 | 400 | 13.3% | Anthropic60.0% |
| z-ai | 1 | 400 | 40.5% | Google58.3% |
| Kwai | 1 | 400 | 46.5% | Qwen31.8% |
| StepFun | 1 | 400 | 89.5% | Meta3.3% |
| Xiaomi | 1 | 400 | 92.8% | Anthropic7.2% |
| Moonshot | 1 | 400 | 99.3% | — |
| xAI | 1 | 400 | 100.0% | — |
| Qwen | 1 | 400 | 100.0% | — |
| ERNIE | 1 | 400 | 100.0% | — |
| Meta | 0 | 0 | 0.0% | — |
 Mistral | 0 | 0 | 0.0% | — |
| Yandex | 0 | 0 | 0.0% | — |
| BAAI | 0 | 0 | 0.0% | — |
| NAVER | 0 | 0 | 0.0% | — |
| 01-ai | 0 | 0 | 0.0% | — |
| Sber | 0 | 0 | 0.0% | — |
| G42 | 0 | 0 | 0.0% | — |
| IBM | 0 | 0 | 0.0% | — |
| バイトビート株式会社 | 0 | 0 | 0.0% | — |
Doubao
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% | 92.5% | 95.0% | 100.0% | 100.0% | 100.0% | 97.5% | 100.0% | 100.0% | 98.5% |
| 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 | 0.0% | 92.5% | 20.0% | 0.0% | 7.5% | 7.5% | 0.0% | 2.5% | 2.5% | 0.0% | 13.3% |
Cross-Vendor Confusions
Doubao Seed 2.0 Pro100.0% self
✓ Always self-identifies correctly
Doubao Seed 2.0 Mini98.5% self
Mistaken as:バイトビート株式会社0.3%OpenAI0.3%
OpenAI0.3%Doubao Seed 2.0 Lite100.0% self
✓ Always self-identifies correctly
Doubao Seed 2.0 Code13.3% self
Mistaken as:OpenAI60.3%Anthropic23.8%Meta1.8%Google1.0%
OpenAI60.3%Anthropic23.8%Meta1.8%Google1.0%Anthropic
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.8 | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| Claude Sonnet 4.6 | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| Claude Haiku 4.5 | 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
Claude Opus 4.8100.0% self
✓ Always self-identifies correctly
Claude Sonnet 4.6100.0% self
✓ Always self-identifies correctly
Claude Haiku 4.5100.0% self
✓ Always self-identifies correctly
OpenAI
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.5 | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 97.5% | 100.0% | 100.0% | 99.8% |
| 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 | 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
GPT-5.599.8% self
✓ Always self-identifies correctly
GPT-5.5 Instant100.0% self
✓ Always self-identifies correctly
GPT 5.3 Codex100.0% self
✓ Always self-identifies correctly
DeepSeek
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | 75.0% | 82.5% | 67.5% | 42.5% | 70.0% | 85.0% | 75.0% | 60.0% | 67.5% | 75.0% | 70.0% |
| DeepSeek V4 Flash | 90.0% | 100.0% | 95.0% | 92.5% | 95.0% | 90.0% | 82.5% | 87.5% | 87.5% | 92.5% | 91.3% |
Cross-Vendor Confusions
DeepSeek V4 Pro70.0% self
Mistaken as:Anthropic18.0%Google8.3%OpenAI1.5%Qwen0.3%xAI0.3%Mistral0.3%
Anthropic18.0%Google8.3%OpenAI1.5%Qwen0.3%xAI0.3%Mistral0.3%DeepSeek V4 Flash91.3% self
Mistaken as:OpenAI6.0%Anthropic0.8%Meta0.5%Qwen0.5%
OpenAI6.0%Anthropic0.8%Meta0.5%Qwen0.5%Google
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
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Ring 2.6 1T | 0.0% | 0.0% | 2.5% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 2.5% | 0.0% | 0.5% |
| Ling 2.6 1T | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% | 0.0% |
Cross-Vendor Confusions
Ring 2.6 1T0.5% self
✓ Always self-identifies correctly
Ling 2.6 1T0.0% self
Mistaken as:Anthropic0.3%Meta0.3%OpenAI0.3%
Anthropic0.3%Meta0.3%OpenAI0.3%MiniMax
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MiniMax 2.7 | 72.5% | 85.0% | 85.0% | 87.5% | 85.0% | 87.5% | 80.0% | 80.0% | 87.5% | 80.0% | 83.0% |
| MiniMax 3 | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 97.5% | 100.0% | 100.0% | 99.8% |
Cross-Vendor Confusions
MiniMax 2.783.0% self
Mistaken as:OpenAI3.5%Anthropic3.0%DeepSeek0.3%
OpenAI3.5%Anthropic3.0%DeepSeek0.3%MiniMax 399.8% self
Mistaken as:OpenAI0.3%
OpenAI0.3%ERNIE
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
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Kat Coder Pro V2 | 45.0% | 100.0% | 100.0% | 52.5% | 0.0% | 0.0% | 67.5% | 12.5% | 25.0% | 62.5% | 46.5% |
Cross-Vendor Confusions
Kat Coder Pro V246.5% self
Mistaken as:Qwen31.8%OpenAI11.0%z-ai3.3%DeepSeek1.8%Doubao1.3%ERNIE0.8%Moonshot0.8%Google0.5%BAAI0.5%Tencent0.3%
Qwen31.8%OpenAI11.0%z-ai3.3%DeepSeek1.8%Doubao1.3%ERNIE0.8%Moonshot0.8%Google0.5%BAAI0.5%Tencent0.3%Moonshot
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% | 97.5% | 95.0% | 100.0% | 100.0% | 100.0% | 99.3% |
Cross-Vendor Confusions
Kimi 2.699.3% self
✓ Always self-identifies correctly
Qwen
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
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flash | 95.0% | 100.0% | 100.0% | 100.0% | 95.0% | 55.0% | 95.0% | 85.0% | 72.5% | 97.5% | 89.5% |
Cross-Vendor Confusions
Step 3.7 Flash89.5% self
Mistaken as:Meta3.3%OpenAI1.3%Google1.3%Anthropic1.0%Mistral0.8%DeepSeek0.8%Qwen0.8%01-ai0.3%Tencent0.3%Sber0.3%xAI0.3%G420.3%IBM0.3%
Meta3.3%OpenAI1.3%Google1.3%Anthropic1.0%Mistral0.8%DeepSeek0.8%Qwen0.8%01-ai0.3%Tencent0.3%Sber0.3%xAI0.3%G420.3%IBM0.3%Tencent
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Hy3 Preview | 0.0% | 95.0% | 2.5% | 0.0% | 0.0% | 30.0% | 0.0% | 0.0% | 5.0% | 0.0% | 13.3% |
Cross-Vendor Confusions
Hy3 Preview13.3% self
Mistaken as:Anthropic60.0%Google16.8%Meta3.5%DeepSeek1.5%OpenAI1.5%xAI1.5%Qwen1.0%Yandex0.5%NAVER0.3%z-ai0.3%
Anthropic60.0%Google16.8%Meta3.5%DeepSeek1.5%OpenAI1.5%xAI1.5%Qwen1.0%Yandex0.5%NAVER0.3%z-ai0.3%xAI
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
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Mimo V2.5 Pro | 100.0% | 95.0% | 90.0% | 92.5% | 97.5% | 90.0% | 92.5% | 92.5% | 95.0% | 82.5% | 92.8% |
Cross-Vendor Confusions
Mimo V2.5 Pro92.8% self
Mistaken as:Anthropic7.2%
Anthropic7.2%z-ai
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| GLM 5.1 | 45.0% | 85.0% | 45.0% | 50.0% | 0.0% | 37.5% | 35.0% | 25.0% | 52.5% | 30.0% | 40.5% |
Cross-Vendor Confusions
GLM 5.140.5% self
Mistaken as:Google58.3%Anthropic1.0%OpenAI0.3%
Google58.3%Anthropic1.0%OpenAI0.3%