Aggregate Performance on Aggregate HotPotQA, LiveBench-Math, Formula
74.3Aggregate ScoreRPT
Evaluation Results
| Method | Links | |
|---|---|---|
| RPTOptimizer LLM=GPT-5, Target Model=GPT-4.12026.05 | 74.3 | |
| ACEOptimizer LLM=GPT-5-mini, Target Model=GPT-4.12026.05 | 71.6 | |
| ACEOptimizer LLM=GPT-5, Target Model=GPT-4.12026.05 | 71.2 | |
| ACEOptimizer LLM=Gemini-3.1-Pro, Target Model=GPT-4.12026.05 | 70.4 | |
| RPTOptimizer LLM=Gemini-3.1-Pro, Target Model=GPT-4.12026.05 | 70.1 | |
| ACEOptimizer LLM=Gemini-3.1-Flash-Lite, Target Model=GPT-4.12026.05 | 68.7 | |
| RPTOptimizer LLM=GPT-5-mini, Target Model=GPT-4.12026.05 | 68.5 | |
| RPTOptimizer LLM=Gemini-3.1-Flash-Lite, Target Model=GPT-4.12026.05 | 67.7 | |
| MIPROOptimizer LLM=GPT-5, Target Model=GPT-4.12026.05 | 63.6 | |
| GEPAOptimizer LLM=Gemini-3.1-Pro, Target Model=GPT-4.12026.05 | 62.9 | |
| MIPROOptimizer LLM=GPT-5-mini, Target Model=GPT-4.12026.05 | 62.3 | |
| GEPAOptimizer LLM=Gemini-3.1-Flash-Lite, Target Model=GPT-4.12026.05 | 61.9 | |
| GEPAOptimizer LLM=GPT-5, Target Model=GPT-4.12026.05 | 61.5 | |
| GEPAOptimizer LLM=GPT-5-mini, Target Model=GPT-4.12026.05 | 61.3 | |
| MIPROOptimizer LLM=Gemini-3.1-Pro, Target Model=GPT-4.12026.05 | 61.3 | |
| MIPROOptimizer LLM=Gemini-3.1-Flash-Lite, Target Model=GPT-4.12026.05 | 60 |