Code Test Generation on MBPP+
80.24Source Pass RateQWEN3-14B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| QWEN3-14BModel=QWEN3-14B2026.03 | 80.24 | 66.5 | 4.35 | |
| MIST-RLModel=MIST-RL2026.03 | 77.54 | 70.27 | 5.17 | |
| CODERM-8BModel=CODERM-8B2026.03 | 72.67 | 61.08 | 6.55 | |
| LLAMA-3-8B-INSTRUCTModel=LLAMA-3-8B-INSTRUCT2026.03 | 42.51 | 22.54 | 2.35 |