Multiple Choice Question Answering on MMLU-PRO (zero-shot)
84.29AccuracyGemini 2.0 Pro Exp
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 2.0 Pro ExpPrompting Strategy=Induct, Zero-shot=true2026.05 | 84.29 | |
| Gemini 2.0 Pro ExpPrompting Strategy=Our, Zero-shot=true2026.05 | 82.86 | |
| Gemini 2.0 Pro ExpPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 82.29 | |
| GPT o3 mini (high)Prompting Strategy=Our, Zero-shot=true2026.05 | 80 | |
| GPT o3 mini (high)Prompting Strategy=ZCoT, Zero-shot=true2026.05 | 79.71 | |
| GPT o3 mini (high)Prompting Strategy=Induct, Zero-shot=true2026.05 | 79.14 | |
| GPT o3 mini (medium)Prompting Strategy=Our, Zero-shot=true2026.05 | 78.57 | |
| GPT o3 mini (medium)Prompting Strategy=ZCoT, Zero-shot=true2026.05 | 77.71 | |
| GPT o3 mini (medium)Prompting Strategy=Induct, Zero-shot=true2026.05 | 77.43 | |
| GPT o3 mini (low)Prompting Strategy=Our, Zero-shot=true2026.05 | 77.14 | |
| GPT-4oPrompting Strategy=Our, Zero-shot=true2026.05 | 76.57 | |
| GPT o3 mini (low)Prompting Strategy=ZCoT, Zero-shot=true2026.05 | 76.57 | |
| Gemini 1.5 ProPrompting Strategy=Our, Zero-shot=true2026.05 | 76.29 | |
| GPT-4oPrompting Strategy=Induct, Zero-shot=true2026.05 | 76 | |
| Gemini 2.0 Flash ThinkingPrompting Strategy=Our, Zero-shot=true2026.05 | 75.71 | |
| Gemini 2.0 Flash ThinkingPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 75.43 | |
| GPT-4oPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 75.14 | |
| Gemini 2.0 Flash ThinkingPrompting Strategy=Induct, Zero-shot=true2026.05 | 75.14 | |
| Gemini 1.5 ProPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 74.86 | |
| GPT o3 mini (low)Prompting Strategy=Induct, Zero-shot=true2026.05 | 74 | |
| Gemini 1.5 ProPrompting Strategy=Induct, Zero-shot=true2026.05 | 73.43 | |
| Llama 3.3 70BPrompting Strategy=Our, Zero-shot=true2026.05 | 71.43 | |
| Llama 3.3 70BPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 70.29 | |
| Gemini 2.0 FlashPrompting Strategy=Our, Zero-shot=true2026.05 | 70.29 | |
| Llama 3.3 70BPrompting Strategy=Induct, Zero-shot=true2026.05 | 69.14 | |
| Mistral Large 2Prompting Strategy=Our, Zero-shot=true2026.05 | 68.86 | |
| Mistral Large 2Prompting Strategy=ZCoT, Zero-shot=true2026.05 | 68.57 | |
| Mistral Large 2Prompting Strategy=Induct, Zero-shot=true2026.05 | 68.57 | |
| Gemini 2.0 Flash LitePrompting Strategy=ZCoT, Zero-shot=true2026.05 | 68.29 | |
| Gemini 2.0 Flash LitePrompting Strategy=Induct, Zero-shot=true2026.05 | 68.29 | |
| Gemini 2.0 Flash LitePrompting Strategy=Our, Zero-shot=true2026.05 | 67.71 | |
| Mistral Small 3Prompting Strategy=Induct, Zero-shot=true2026.05 | 67.43 | |
| Mistral Small 3Prompting Strategy=Our, Zero-shot=true2026.05 | 66.29 | |
| Gemini 1.5 FlashPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 66 | |
| Gemini 1.5 FlashPrompting Strategy=Our, Zero-shot=true2026.05 | 65.71 | |
| Gemini 1.5 FlashPrompting Strategy=Induct, Zero-shot=true2026.05 | 65.14 | |
| Mistral Small 3Prompting Strategy=ZCoT, Zero-shot=true2026.05 | 64.86 | |
| Gemini 2.0 FlashPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 63.14 | |
| GPT-4o miniPrompting Strategy=Induct, Zero-shot=true2026.05 | 63.14 | |
| Gemini 2.0 FlashPrompting Strategy=Induct, Zero-shot=true2026.05 | 62.86 | |
| GPT-4o miniPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 62.29 | |
| GPT-4o miniPrompting Strategy=Our, Zero-shot=true2026.05 | 60.57 | |
| Gemini 1.5 Flash 8BPrompting Strategy=Our, Zero-shot=true2026.05 | 54.57 | |
| Gemini 1.5 Flash 8BPrompting Strategy=Induct, Zero-shot=true2026.05 | 53.71 | |
| Gemini 1.5 Flash 8BPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 52.29 | |
| Mistral Small 2Prompting Strategy=ZCoT, Zero-shot=true2026.05 | 49.71 | |
| Mistral Small 2Prompting Strategy=Induct, Zero-shot=true2026.05 | 47.14 | |
| Mistral Small 2Prompting Strategy=Our, Zero-shot=true2026.05 | 46.86 | |
| Llama 3.1 8BPrompting Strategy=Induct, Zero-shot=true2026.05 | 44 | |
| Llama 3.1 8BPrompting Strategy=Our, Zero-shot=true2026.05 | 42 | |
| Llama 3.1 8BPrompting Strategy=ZCoT, Zero-shot=true2026.05 | 41.71 |