List your company

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

93AccuracyOpenAI-o3-mini
1.4825.244972.76Feb 18, 2025

Evaluation results

MethodLinks
OpenAI-o3-miniScenario=base, Setup=Zero-shot2025.0293—
Claude-3.5-SonnetScenario=base, Setup=Zero-shot2025.0289—
GPT-4-TurboScenario=base, Setup=Zero-shot2025.0285—
GPT-4oScenario=base, Setup=Zero-shot2025.0284—
OpenAI-o3-miniScenario=NOTO, Setup=Zero-shot2025.027915.05
DeepSeek-R1-70BScenario=base, Setup=Zero-shot2025.0277—
Llama-3-70B-InstructScenario=base, Setup=Zero-shot2025.0277—
Gemma-2-27B-InstructScenario=base, Setup=Zero-shot2025.0276—
Mixtral-8x22B-InstructScenario=base, Setup=Zero-shot2025.0274—
Mixtral-8x7B-InstructScenario=base, Setup=Zero-shot2025.0270—
GPT-4oScenario=NOTO, Setup=Zero-shot2025.026917.86
GPT-3.5-TurboScenario=base, Setup=Zero-shot2025.0268—
DeepSeek-R1-70BScenario=NOTO, Setup=Zero-shot2025.026515.58
GPT-4-TurboScenario=NOTO, Setup=Zero-shot2025.026523.53
Llama-3-8B-InstructScenario=base, Setup=Zero-shot2025.0265—
Claude-3.5-SonnetScenario=NOTO, Setup=Zero-shot2025.026230.34
Mistral-7B-InstructScenario=base, Setup=Zero-shot2025.0260—
Gemma-7B-InstructScenario=base, Setup=Zero-shot2025.0256—
Llama-2-7B-ChatScenario=base, Setup=Zero-shot2025.0248—
Salamandra-7B-InstructScenario=base, Setup=Zero-shot2025.0246—
Gemma-2-27B-InstructScenario=NOTO, Setup=Zero-shot2025.024146.05
Llama-3-70B-InstructScenario=NOTO, Setup=Zero-shot2025.024146.75
Leniachat-Gemma-2BScenario=base, Setup=Zero-shot2025.0237—
Mistral-7B-InstructScenario=NOTO, Setup=Zero-shot2025.023443.33
Mixtral-8x7B-InstructScenario=NOTO, Setup=Zero-shot2025.023352.86
Llama-3-8B-InstructScenario=NOTO, Setup=Zero-shot2025.023349.23
Mixtral-8x22B-InstructScenario=NOTO, Setup=Zero-shot2025.022566.22
Salamandra-7B-InstructScenario=NOTO, Setup=Zero-shot2025.021665.22
Llama-2-7B-ChatScenario=NOTO, Setup=Zero-shot2025.021568.75
GPT-3.5-TurboScenario=NOTO, Setup=Zero-shot2025.021085.29
Gemma-7B-InstructScenario=NOTO, Setup=Zero-shot2025.02983.93
Leniachat-Gemma-2BScenario=NOTO, Setup=Zero-shot2025.02586.49