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

Multiple Choice Question Answering on UNED-Access English 2024 (test)

92Accuracy

OpenAI-o3-mini

Updated 19d ago

Evaluation Results

Method	Links
OpenAI-o3-mini 2025.02		92	-
Claude-3.5-Sonnet 2025.02		87	-
GPT-4o 2025.02		85	-
GPT-4-Turbo 2025.02		84	-
OpenAI-o3-mini 2025.02		77	16.3
Gemma-2-27B-Instruct 2025.02		75	-
Llama-3-70B-Instruct 2025.02		75	-
Mixtral-8x22B-Instruct 2025.02		73	-
GPT-3.5-Turbo 2025.02		72	-
GPT-4o 2025.02		69	18.82
Mixtral-8x7B-Instruct 2025.02		69	-
Llama-3-8B-Instruct 2025.02		66	-
Mistral-7B-Instruct 2025.02		62	-
DeepSeek-R1-70B 2025.02		60	-
Gemma-7B-Instruct 2025.02		59	-
GPT-4-Turbo 2025.02		58	30.95
DeepSeek-R1-70B 2025.02		54	10
Claude-3.5-Sonnet 2025.02		53	39.08
Llama-2-7B-Chat 2025.02		52	-
Salamandra-7B-Instruct 2025.02		47	-
Llama-3-70B-Instruct 2025.02		41	45.33
Gemma-2-27B-Instruct 2025.02		40	46.67
Leniachat-Gemma-2B 2025.02		40	-
Mixtral-8x7B-Instruct 2025.02		37	46.38
Llama-3-8B-Instruct 2025.02		37	43.94
Mistral-7B-Instruct 2025.02		33	46.77
Llama-2-7B-Chat 2025.02		26	50
Mixtral-8x22B-Instruct 2025.02		19	73.97
GPT-3.5-Turbo 2025.02		14	80.56
Salamandra-7B-Instruct 2025.02		11	76.6
Gemma-7B-Instruct 2025.02		9	84.75
Leniachat-Gemma-2B 2025.02		3	92.5