Domain Knowledge Evaluation on MMLU HS US History (test)
93.93AccuracyCOPRO
Evaluation Results
| Method | Links | |
|---|---|---|
| COPROBackbone Model=Gemini-2-Flash, Prompt Optimization Technique=COPRO2026.05 | 93.93 | |
| GEPABackbone Model=Gemini-2-Flash, Prompt Optimization Technique=GEPA2026.05 | 93.28 | |
| MIPROBackbone Model=Gemini-2-Flash, Prompt Optimization Technique=MIPRO2026.05 | 91.64 | |
| PSAO_LLMBackbone Model=Gemini-2-Flash, Prompt Optimization Technique=PSAO_LLM2026.05 | 88.52 | |
| BaselineBackbone Model=Gemini-2-Flash, Prompt Optimization Technique=Baseline2026.05 | 87.3 | |
| ProTeGiBackbone Model=Gemini-2-Flash, Prompt Optimization Technique=ProTeGi2026.05 | 85.74 | |
| PromptAgentBackbone Model=Gemini-2-Flash, Prompt Optimization Technique=PromptAgent2026.05 | 83.93 |