Code Test Generation on HumanEval+
74.86Source Pass RateMIST-RL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MIST-RLModel=MIST-RL2026.03 | 74.86 | 74.03 | 6.14 | |
| QWEN3-14BModel=QWEN3-14B2026.03 | 74.31 | 58.69 | 5.12 | |
| CODERM-8BModel=CODERM-8B2026.03 | 70.61 | 45.53 | 7.61 | |
| LLAMA-3-8B-INSTRUCTModel=LLAMA-3-8B-INSTRUCT2026.03 | 40.99 | 29.18 | 2.33 |