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

Multiple Choice Question Answering on MMLU Spanish (test)

86Accuracy

OpenAI-o3-mini

Updated 19d ago

Evaluation Results

Method	Links
OpenAI-o3-mini 2025.02		86	-
Claude-3.5-Sonnet 2025.02		85	-
GPT-4o 2025.02		82	-
GPT-4-Turbo 2025.02		78	-
Llama-3-70B-Instruct 2025.02		73	-
DeepSeek-R1-70B 2025.02		72	-
Gemma-2-27B-Instruct 2025.02		72	-
Mixtral-8x22B-Instruct 2025.02		67	-
Mixtral-8x7B-Instruct 2025.02		64	-
OpenAI-o3-mini 2025.02		60	30.23
GPT-3.5-Turbo 2025.02		60	-
GPT-4o 2025.02		56	31.71
Llama-3-8B-Instruct 2025.02		56	-
GPT-4-Turbo 2025.02		53	32.05
Mistral-7B-Instruct 2025.02		51	-
DeepSeek-R1-70B 2025.02		44	38.89
Gemma-7B-Instruct 2025.02		44	-
Claude-3.5-Sonnet 2025.02		43	49.41
Llama-2-7B-Chat 2025.02		38	-
Salamandra-7B-Instruct 2025.02		36	-
Leniachat-Gemma-2B 2025.02		30	-
Gemma-2-27B-Instruct 2025.02		28	61.11
Llama-3-70B-Instruct 2025.02		25	65.75
Llama-3-8B-Instruct 2025.02		23	58.93
Mixtral-8x7B-Instruct 2025.02		22	65.63
Llama-2-7B-Chat 2025.02		21	44.74
Mistral-7B-Instruct 2025.02		20	60.78
Mixtral-8x22B-Instruct 2025.02		16	76.12
Salamandra-7B-Instruct 2025.02		14	61.11
Gemma-7B-Instruct 2025.02		8	81.82
GPT-3.5-Turbo 2025.02		8	86.67
Leniachat-Gemma-2B 2025.02		3	90