Acumen Cognitive Engineering

The AI sector is moving into a phase where numerous foundational models will be accessible, accompanied by a variety of specialized models tailored for specific tasks. This shift presents a fresh challenge, highlighting the necessity for more robust and dependable benchmarks.

Claude 2 (Anthropic)
GPT-4 (OpenAI)
Mistral 7B (Mistral)
LLaMA 2 (Meta)
Gemini 1 (Google DeepMind)
Claude 1 (Anthropic)
GPT-3.5 (OpenAI)
LLaMA (Meta)
ERNIE 4.0 (Baidu)
Falcon 40B (Technology Innovation Institute)
BLOOM (BigScience)
GLaM (Google)
OPT (Meta)
GLM-130B (Tsinghua University)
Chinchilla (DeepMind)
Jurassic-1 (AI21 Labs)
T5 (Google)
Gopher (DeepMind)
HyperCLOVA (NAVER) Claude 2 (Anthropic)
GPT-4 (OpenAI)
Mistral 7B (Mistral)
LLaMA 2 (Meta)
Gemini 1 (Google DeepMind)
Claude 1 (Anthropic)
GPT-3.5 (OpenAI)
LLaMA (Meta)
ERNIE 4.0 (Baidu)
Falcon 40B (Technology Innovation Institute)
BLOOM (BigScience)
GLaM (Google)
OPT (Meta)
GLM-130B (Tsinghua University)
Chinchilla (DeepMind)
Jurassic-1 (AI21 Labs)
T5 (Google)
Gopher (DeepMind)
HyperCLOVA (NAVER)