Code Reasoning on CRUXEval I
74AccuracyKimi-K2 Base
Evaluation Results
| Method | Links | |
|---|---|---|
| Kimi-K2 Base# Shots=1-shot, # Activated Params=32B, # Total Params=1043B2026.01 | 74 | |
| MiMo-V2-Flash Base# Shots=1-shot, # Activated Params=15B, # Total Params=309B2026.01 | 67.5 | |
| DeepSeek-V3.2 Exp Base# Shots=1-shot, # Activated Params=37B, # Total Params=671B2026.01 | 63.9 | |
| DeepSeek-V3.1 Base# Shots=1-shot, # Activated Params=37B, # Total Params=671B2026.01 | 62.1 | |
| Qwen3.5-4BParameters=4B2026.05 | 49.1 | |
| Mellum 2Parameters=2.5B/12B2026.05 | 45.4 | |
| Qwen3-4BParameters=4B2026.05 | 44.6 | |
| Qwen2.5-7BParameters=7B2026.05 | 44 | |
| OLMo-3-7BParameters=7B2026.05 | 38.8 |