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

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

93Accuracy

OpenAI-o3-mini

Updated 19d ago

Evaluation Results

Method	Links
OpenAI-o3-mini 2025.02		93	-
Claude-3.5-Sonnet 2025.02		89	-
GPT-4-Turbo 2025.02		85	-
GPT-4o 2025.02		84	-
OpenAI-o3-mini 2025.02		79	15.05
DeepSeek-R1-70B 2025.02		77	-
Llama-3-70B-Instruct 2025.02		77	-
Gemma-2-27B-Instruct 2025.02		76	-
Mixtral-8x22B-Instruct 2025.02		74	-
Mixtral-8x7B-Instruct 2025.02		70	-
GPT-4o 2025.02		69	17.86
GPT-3.5-Turbo 2025.02		68	-
DeepSeek-R1-70B 2025.02		65	15.58
GPT-4-Turbo 2025.02		65	23.53
Llama-3-8B-Instruct 2025.02		65	-
Claude-3.5-Sonnet 2025.02		62	30.34
Mistral-7B-Instruct 2025.02		60	-
Gemma-7B-Instruct 2025.02		56	-
Llama-2-7B-Chat 2025.02		48	-
Salamandra-7B-Instruct 2025.02		46	-
Gemma-2-27B-Instruct 2025.02		41	46.05
Llama-3-70B-Instruct 2025.02		41	46.75
Leniachat-Gemma-2B 2025.02		37	-
Mistral-7B-Instruct 2025.02		34	43.33
Mixtral-8x7B-Instruct 2025.02		33	52.86
Llama-3-8B-Instruct 2025.02		33	49.23
Mixtral-8x22B-Instruct 2025.02		25	66.22
Salamandra-7B-Instruct 2025.02		16	65.22
Llama-2-7B-Chat 2025.02		15	68.75
GPT-3.5-Turbo 2025.02		10	85.29
Gemma-7B-Instruct 2025.02		9	83.93
Leniachat-Gemma-2B 2025.02		5	86.49