Data Explorer
Per-model self-identification rates across languages, grouped by vendor. 645 cross-vendor confusions detected.
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.
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.
Self-ID and refusal rates per language, plus the most common cross-vendor confusion at that language.
| Language | Self-ID | Refused | Top confusion |
|---|---|---|---|
| ko한국어 | 80.3% | 6.3% | OpenAI100.0% |
| ja日本語 | 82.4% | 5.4% | OpenAI100.0% |
| ruРусский | 82.4% | 6.5% | OpenAI90.0% |
| frFrançais | 86.3% | 1.6% | OpenAI96.7% |
| ptPortuguês | 87.0% | 2.1% | OpenAI96.7% |
| esEspañol | 87.1% | 1.4% | OpenAI93.3% |
| zh-Hant繁體中文 | 88.6% | 1.9% | OpenAI86.7% |
| enEnglish | 88.9% | 1.3% | OpenAI100.0% |
| deDeutsch | 89.0% | 1.3% | OpenAI93.3% |
| zh-Hans简体中文 | 94.0% | 1.7% | OpenAI53.3% |
How the same “Who are you?” question splits into correct self-ID vs. confusion vs. abstention — per language, worst self-ID first.
Self-identification is lowest in 한국어 at 80.3% and highest in 简体中文 at 94.0%.
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.
The other failure mode — not answering wrong, but not answering: giving no identity (“unknown”) or refusing outright. Share of all answers.
inclusionAI abstains most, with 34.0% of answers giving no usable identity.
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 |
|---|---|---|---|---|
| Anthropic | 3 | 900 | 100.0% | — |
| OpenAI | 3 | 900 | 100.0% | — |
| Xiaomi | 2 | 600 | 96.0% | Mistral1.3% |
| z-ai | 2 | 600 | 99.3% | Moonshot0.2% |
| DeepSeek | 1 | 300 | 7.0% | OpenAI91.0% |
| LongCat | 1 | 300 | 14.7% | Anthropic31.7% |
| MiniMax | 1 | 300 | 45.7% | OpenAI28.0% |
| inclusionAI | 1 | 300 | 66.0% | — |
| Mistral | 1 | 300 | 96.7% | Google1.0% |
| xAI | 1 | 300 | 98.3% | Anthropic0.7% |
| StepFun | 1 | 300 | 99.7% | Google0.3% |
| Meta | 1 | 300 | 100.0% | — |
| 1 | 300 | 100.0% | — | |
| Moonshot | 1 | 300 | 100.0% | — |
| Sakana AI | 1 | 300 | 100.0% | — |
| Qwen | 0 | 0 | 0.0% | — |
| ERNIE | 0 | 0 | 0.0% | — |
| Amazon Web Services | 0 | 0 | 0.0% | — |
| XSpark | 0 | 0 | 0.0% | — |
| SpaceXAI & Cursor | 0 | 0 | 0.0% | — |
| Lenovo | 0 | 0 | 0.0% | — |
| SpaceXAI and Cursor | 0 | 0 | 0.0% | — |
| Lambda | 0 | 0 | 0.0% | — |
| Microsoft | 0 | 0 | 0.0% | — |
| Starlink | 0 | 0 | 0.0% | — |
| Sber | 0 | 0 | 0.0% | — |
| AWS | 0 | 0 | 0.0% | — |
| Sber AI | 0 | 0 | 0.0% | — |
| Zepo.ai | 0 | 0 | 0.0% | — |
| Innate Cloud | 0 | 0 | 0.0% | — |
| Sepia | 0 | 0 | 0.0% | — |
| 3StepAI | 0 | 0 | 0.0% | — |
| Naver | 0 | 0 | 0.0% | — |
| Huawei Cloud | 0 | 0 | 0.0% | — |
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| Claude Sonnet 5.5 | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| Claude Opus 5.5 | 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
✓ Always self-identifies correctly
✓ Always self-identifies correctly
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-6.1 Terra | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| GPT-6.1 Sol | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% |
| GPT-6 Luna | 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
✓ Always self-identifies correctly
✓ Always self-identifies correctly
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MiMo V2.6 Flash | 100.0% | 100.0% | 100.0% | 100.0% | 93.3% | 96.7% | 96.7% | 86.7% | 100.0% | 100.0% | 97.3% |
| MiMo V2.6 Pro | 100.0% | 100.0% | 100.0% | 96.7% | 93.3% | 83.3% | 100.0% | 76.7% | 100.0% | 96.7% | 94.7% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| GLM 5.3 Prime | 100.0% | 100.0% | 100.0% | 93.3% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 99.3% |
| GLM 5.3 FlashX | 100.0% | 100.0% | 96.7% | 100.0% | 100.0% | 100.0% | 100.0% | 96.7% | 100.0% | 100.0% | 99.3% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 0.0% | 46.7% | 13.3% | 0.0% | 0.0% | 3.3% | 3.3% | 0.0% | 3.3% | 0.0% | 7.0% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 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
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Ling 3.1 Flash | 100.0% | 100.0% | 96.7% | 0.0% | 0.0% | 0.0% | 93.3% | 86.7% | 100.0% | 83.3% | 66.0% |
Cross-Vendor Confusions
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| LongCat 2.5 Preview | 0.0% | 96.7% | 33.3% | 3.3% | 3.3% | 0.0% | 0.0% | 3.3% | 6.7% | 0.0% | 14.7% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Muse Wonder 1.0 | 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
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| MiniMax M3.1 Flash | 66.7% | 46.7% | 20.0% | 43.3% | 23.3% | 50.0% | 36.7% | 63.3% | 60.0% | 46.7% | 45.7% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Mistral Large 4 | 100.0% | 93.3% | 100.0% | 96.7% | 76.7% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 96.7% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K3.1 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
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Fugu Ultra v2 | 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
✓ Always self-identifies correctly
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Step 5 Preview | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 96.7% | 100.0% | 100.0% | 100.0% | 100.0% | 99.7% |
Cross-Vendor Confusions
Self-Identification Rate
| Model | en | zh-Hans | zh-Hant | ja | ko | ru | es | fr | de | pt | Overall |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Grok 4.7 | 100.0% | 90.0% | 100.0% | 96.7% | 96.7% | 100.0% | 100.0% | 100.0% | 100.0% | 100.0% | 98.3% |