List your company

Multiple Choice Question Answering on MMLU English (test)

89AccuracyOpenAI-o3-mini
-0.4422.784669.22Feb 18, 2025

Evaluation results

MethodLinks
OpenAI-o3-miniScenario=base, Setup=Zero-shot2025.0289—
Claude-3.5-SonnetScenario=base, Setup=Zero-shot2025.0286—
GPT-4oScenario=base, Setup=Zero-shot2025.0284—
GPT-4-TurboScenario=base, Setup=Zero-shot2025.0281—
Llama-3-70B-InstructScenario=base, Setup=Zero-shot2025.0278—
Gemma-2-27B-InstructScenario=base, Setup=Zero-shot2025.0275—
Mixtral-8x22B-InstructScenario=base, Setup=Zero-shot2025.0273—
DeepSeek-R1-70BScenario=base, Setup=Zero-shot2025.0272—
Mixtral-8x7B-InstructScenario=base, Setup=Zero-shot2025.0268—
GPT-3.5-TurboScenario=base, Setup=Zero-shot2025.0266—
OpenAI-o3-miniScenario=NOTO, Setup=Zero-shot2025.026526.97
Llama-3-8B-InstructScenario=base, Setup=Zero-shot2025.0264—
DeepSeek-R1-70BScenario=NOTO, Setup=Zero-shot2025.026016.67
Mistral-7B-InstructScenario=base, Setup=Zero-shot2025.0259—
GPT-4oScenario=NOTO, Setup=Zero-shot2025.025830.95
GPT-4-TurboScenario=NOTO, Setup=Zero-shot2025.025137.04
Gemma-7B-InstructScenario=base, Setup=Zero-shot2025.0249—
Llama-2-7B-ChatScenario=base, Setup=Zero-shot2025.0240—
Claude-3.5-SonnetScenario=NOTO, Setup=Zero-shot2025.024053.49
Salamandra-7B-InstructScenario=base, Setup=Zero-shot2025.0238—
Gemma-2-27B-InstructScenario=NOTO, Setup=Zero-shot2025.023257.33
Leniachat-Gemma-2BScenario=base, Setup=Zero-shot2025.0232—
Llama-3-70B-InstructScenario=NOTO, Setup=Zero-shot2025.023061.54
Llama-2-7B-ChatScenario=NOTO, Setup=Zero-shot2025.022927.5
Mixtral-8x7B-InstructScenario=NOTO, Setup=Zero-shot2025.022957.35
Llama-3-8B-InstructScenario=NOTO, Setup=Zero-shot2025.022659.38
Mistral-7B-InstructScenario=NOTO, Setup=Zero-shot2025.021869.49
Mixtral-8x22B-InstructScenario=NOTO, Setup=Zero-shot2025.021678.08
Salamandra-7B-InstructScenario=NOTO, Setup=Zero-shot2025.021171.05
GPT-3.5-TurboScenario=NOTO, Setup=Zero-shot2025.02986.36
Gemma-7B-InstructScenario=NOTO, Setup=Zero-shot2025.02785.71
Leniachat-Gemma-2BScenario=NOTO, Setup=Zero-shot2025.02390.63