Accuracy on MMLU & MMLU-Pro
77.95AccuracyQ-Opt + P-Opt
Evaluation Results
| Method | Links | |
|---|---|---|
| Q-Opt + P-OptImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 77.95 | |
| Q + P-OptImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 75.7 | |
| Q-Opt + CoTImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 74.75 | |
| PE2Implementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 74.4 | |
| MARSImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 74.27 | |
| Q-OptImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 73.74 | |
| OPROImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 73.4 | |
| CoTImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 72.68 | |
| APEImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 71.21 | |
| No PromptImplementation Model=Gemini-2.5-Pro, Target LLM=Gemini-2.0-Flash2026.03 | 69.72 |