Software Engineering on SWE-Bench AgentLess Repair
30.8Resolved PercentageMiMo-V2-Flash Base
Evaluation Results
| Method | Links | |
|---|---|---|
| MiMo-V2-Flash Base# Shots=3-shot, # Activated Params=15B, # Total Params=309B2026.01 | 30.8 | |
| Kimi-K2 Base# Shots=3-shot, # Activated Params=32B, # Total Params=1043B2026.01 | 28.2 | |
| DeepSeek-V3.1 Base# Shots=3-shot, # Activated Params=37B, # Total Params=671B2026.01 | 24.8 | |
| DeepSeek-V3.2 Exp Base# Shots=3-shot, # Activated Params=37B, # Total Params=671B, Note=Does not follow the format of few-shot examples2026.01 | 9.4 |