$ ls models/
Models
26 models
Every model a test can identify, and what else it can check. Reference answers come from each model's own provider. The newer GPT and Claude models have no refusal check: their weights aren't published, so nobody can abliterate them.
Model
Identity
Competence
Refusal
GLM 5.3 Z.AI
✓
✓
✓
GLM 5.3 Flash Z.AI
✓
✓
✓
DeepSeek V4.1 Flash DeepSeek
✓
✓
✓
Kimi K3 Moonshot AI
✓
✓
✓
MiMo-V2.6-Flash Xiaomi
✓
–
✓
MiMo-V2.6-Pro Xiaomi
✓
–
✓
MiMo-V2.5 Xiaomi
✓
–
✓
Hy3 Tencent
✓
–
✓
MiniMax M3 MiniMax
✓
–
✓
Qwen3.8 27B Alibaba
✓
–
✓
Gemini 3.8 Flash Google AI Studio
✓
–
✓
Gemini 2.5 Flash Google AI Studio
✓
–
✓
GPT-6 Luna OpenAI
✓
–
✓
GPT-6.1 Sol OpenAI
✓
–
–
GPT-6 Sol OpenAI
✓
–
–
GPT-6 Astra OpenAI
✓
–
–
GPT-5.6 Luna OpenAI
✓
–
–
GPT-5.6 Terra OpenAI
✓
–
–
GPT-5.6 Sol OpenAI
✓
–
–
Claude Fable 5.1 Anthropic
✓
–
–
Claude Fable 5 Anthropic
✓
–
–
Claude Opus 5.5 Anthropic
✓
–
–
Claude Opus 5 Anthropic
✓
–
–
Claude Sonnet 5.5 Anthropic
✓
–
–
Claude Sonnet 5 Anthropic
✓
–
–
Claude Haiku 5.5 Anthropic
✓
–
–