Code Generation on xCodeEval
81.13Pass@1GEPA
Evaluation Results
| Method | Links | |
|---|---|---|
| GEPASource Model=GPT-4o, Target Model=o4-mini2025.12 | 81.13 | |
| PromptBridgeSource Model=GPT-4o, Target Model=o4-mini2025.12 | 77.67 | |
| PromptBridgeSource Model=GPT-4o, Target Model=o32025.12 | 74.84 | |
| MIPROv2Source Model=GPT-4o, Target Model=o4-mini2025.12 | 74.84 | |
| GPT-5 OptimizerSource Model=GPT-4o, Target Model=o4-mini2025.12 | 74.53 | |
| GPT-5 OptimizerSource Model=GPT-4o, Target Model=o32025.12 | 72.64 | |
| Direct TransferSource Model=GPT-4o, Target Model=o4-mini2025.12 | 72.01 | |
| GEPASource Model=GPT-4o, Target Model=o32025.12 | 69.49 | |
| Direct TransferSource Model=GPT-4o, Target Model=o32025.12 | 66.04 | |
| MIPROv2Source Model=GPT-4o, Target Model=o32025.12 | 65.09 | |
| GPT-4oModel Role=Source Model2025.12 | 37.03 | |
| GPT-4oSource Model=GPT-4o, Evaluation Context=Source Performance Reference2025.12 | 37.03 | |
| GPT-5 OptimizerSource Model=GPT-4o, Target Model=Gemma3-27B-it2025.12 | 24.8 | |
| PromptBridgeSource Model=GPT-4o, Target Model=Llama3.1-70B-Instruct2025.12 | 24.53 | |
| GPT-5 OptimizerSource Model=GPT-4o, Target Model=Llama3.1-70B-Instruct2025.12 | 23.58 | |
| PromptBridgeSource Model=GPT-4o, Target Model=Gemma3-27B-it2025.12 | 23.58 | |
| Direct TransferSource Model=GPT-4o, Target Model=Gemma3-27B-it2025.12 | 22.64 | |
| GEPASource Model=GPT-4o, Target Model=Llama3.1-70B-Instruct2025.12 | 22.01 | |
| PromptBridgeSource Model=GPT-4o, Target Model=Qwen3-32B2025.12 | 21.7 | |
| Direct TransferSource Model=GPT-4o, Target Model=Llama3.1-70B-Instruct2025.12 | 21.38 | |
| GPT-5 OptimizerSource Model=GPT-4o, Target Model=Qwen3-32B2025.12 | 19.5 | |
| MIPROv2Source Model=GPT-4o, Target Model=Llama3.1-70B-Instruct2025.12 | 18.87 | |
| Direct TransferSource Model=GPT-4o, Target Model=Qwen3-32B2025.12 | 17.61 | |
| GPT-5 OptimizerSource Model=GPT-4o, Target Model=Llama3.1-8B-Instruct2025.12 | 11.32 | |
| PromptBridgeSource Model=GPT-4o, Target Model=Llama3.1-8B-Instruct2025.12 | 9.43 | |
| Direct TransferSource Model=GPT-4o, Target Model=Llama3.1-8B-Instruct2025.12 | 6.6 | |
| MapCoderLLM=GPT-42024.05 | 0.453 | |
| CoTLLM=GPT-42024.05 | 0.368 | |
| Self-PlanningLLM=GPT-42024.05 | 0.34 | |
| DirectLLM=GPT-42024.05 | 0.321 | |
| MapCoderLLM=ChatGPT2024.05 | 0.274 | |
| AnalogicalLLM=GPT-42024.05 | 0.264 | |
| CoTLLM=ChatGPT2024.05 | 0.236 | |
| Self-PlanningLLM=ChatGPT2024.05 | 0.189 | |
| DirectLLM=ChatGPT2024.05 | 0.179 | |
| AnalogicalLLM=ChatGPT2024.05 | 0.151 |