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

Multiple Choice Question Answering on MMLU English (test)

89Accuracy

OpenAI-o3-mini

Updated 20d ago

Evaluation Results

Method	Links
OpenAI-o3-mini 2025.02		89	-
Claude-3.5-Sonnet 2025.02		86	-
GPT-4o 2025.02		84	-
GPT-4-Turbo 2025.02		81	-
Llama-3-70B-Instruct 2025.02		78	-
Gemma-2-27B-Instruct 2025.02		75	-
Mixtral-8x22B-Instruct 2025.02		73	-
DeepSeek-R1-70B 2025.02		72	-
Mixtral-8x7B-Instruct 2025.02		68	-
GPT-3.5-Turbo 2025.02		66	-
OpenAI-o3-mini 2025.02		65	26.97
Llama-3-8B-Instruct 2025.02		64	-
DeepSeek-R1-70B 2025.02		60	16.67
Mistral-7B-Instruct 2025.02		59	-
GPT-4o 2025.02		58	30.95
GPT-4-Turbo 2025.02		51	37.04
Gemma-7B-Instruct 2025.02		49	-
Llama-2-7B-Chat 2025.02		40	-
Claude-3.5-Sonnet 2025.02		40	53.49
Salamandra-7B-Instruct 2025.02		38	-
Gemma-2-27B-Instruct 2025.02		32	57.33
Leniachat-Gemma-2B 2025.02		32	-
Llama-3-70B-Instruct 2025.02		30	61.54
Llama-2-7B-Chat 2025.02		29	27.5
Mixtral-8x7B-Instruct 2025.02		29	57.35
Llama-3-8B-Instruct 2025.02		26	59.38
Mistral-7B-Instruct 2025.02		18	69.49
Mixtral-8x22B-Instruct 2025.02		16	78.08
Salamandra-7B-Instruct 2025.02		11	71.05
GPT-3.5-Turbo 2025.02		9	86.36
Gemma-7B-Instruct 2025.02		7	85.71
Leniachat-Gemma-2B 2025.02		3	90.63