Share your thoughts, 1 month free Claude Pro on usSee more

Safety Classification on AUTALIC (test)

37.7F1 Score

GPT-OSS

Updated 7d ago

Evaluation Results

Method	Links
GPT-OSS 2026.05		37.7
GPT-OSS 2026.05		34.6
LLaMA Guard3 2026.05		34.2
StarlingLM 2026.05		34.1
LLaMA Guard3 2026.05		33.2
LLaMA Guard3 2026.05		33.1
LLaMA Guard3 2026.05		31.6
StarlingLM 2026.05		31.5
LLaMA Guard3 2026.05		30.7
LLaMA Guard3 2026.05		30
DeepSeek-R1 2026.05		29.7
StarlingLM 2026.05		28.9
GPT-OSS 2026.05		27.9
DeepSeek-R1 2026.05		27.7
GPT-OSS 2026.05		26.7
StarlingLM 2026.05		26.6
DeepSeek-R1 2026.05		26.2
StarlingLM 2026.05		26
DeepSeek-R1 2026.05		25.8
GPT-OSS 2026.05		25.7
LLaMA Guard3 2026.05		25.6
Dolphin Mistral 2026.05		25.2
Dolphin Mistral 2026.05		25.2
Dolphin Mistral 2026.05		25.1
GPT-OSS 2026.05		24.8
DeepSeek-R1 2026.05		24.8
Mistral NeMo 2026.05		24.8
Mistral NeMo 2026.05		24.7
DeepSeek-R1 2026.05		24.6
Dolphin LLaMA3 2026.05		24
DeepSeek-R1 2026.05		23.7
DeepSeek-R1 2026.05		23.7
Dolphin LLaMA3 2026.05		23.6
GPT-OSS 2026.05		23.5
Mistral NeMo 2026.05		22.6
Dolphin Mistral 2026.05		22.4
Mistral NeMo 2026.05		22.4
GPT-OSS 2026.05		22
LLaMA Guard3 2026.05		21.9
Mistral NeMo 2026.05		21.5
StarlingLM 2026.05		21.2
Dolphin Mistral 2026.05		21
Dolphin LLaMA3 2026.05		20.6
Mistral NeMo 2026.05		20.6
Dolphin LLaMA3 2026.05		20.5
Dolphin LLaMA3 2026.05		20.4
StarlingLM 2026.05		19.8
StarlingLM 2026.05		19.8
Dolphin Mistral 2026.05		19.4
Dolphin LLaMA3 2026.05		19
Dolphin LLaMA3 2026.05		18.4
Gemma 3 2026.05		18.4
Mistral NeMo 2026.05		17.8
Mistral NeMo 2026.05		17.8
Dolphin LLaMA3 2026.05		17.4
Gemma 3 2026.05		17.4
Gemma 3 2026.05		17.3
Gemma 3 2026.05		17.2
Gemma 3 2026.05		17
Gemma 3 2026.05		16.8
Gemma 3 2026.05		16.8
Gemma 3 2026.05		15.5
Dolphin Mistral 2026.05		15.3
Dolphin Mistral 2026.05		14.3