Program Synthesis on MBPP-EvalPlus Standard (test)
79.9Pass@1QualityFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| QualityFlowLLM Backbone=Claude Sonnet-3.5-v22025.01 | 79.9 | 3.7 | |
| DeepSeek-Coder-V2-Instruct2025.01 | 76.2 | — |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| QualityFlowLLM Backbone=Claude Sonnet-3.5-v22025.01 | 79.9 | 3.7 | |
| DeepSeek-Coder-V2-Instruct2025.01 | 76.2 | — |