Factuality on SimpleQA
35.3Factuality ScoreKimi-K2
Evaluation Results
| Method | Links | |
|---|---|---|
| Kimi-K2Model Variant=Base, # Shots=5-shot, # Activated Params=32B, # Total Params=1043B2026.02 | 35.3 | |
| Step 3.5 FlashModel Variant=Base, # Shots=5-shot, # Activated Params=11B, # Total Params=196B2026.02 | 31.6 | |
| GLM-4.5Model Variant=Base, # Shots=5-shot, # Activated Params=32B, # Total Params=355B2026.02 | 30 | |
| DeepSeek V3.2Model Variant=Exp Base, # Shots=5-shot, # Activated Params=37B, # Total Params=671B2026.02 | 27 | |
| DeepSeek V3.1Model Variant=Base, # Shots=5-shot, # Activated Params=37B, # Total Params=671B2026.02 | 26.3 | |
| Trinity Large Previewtuning=instruct-tuned2026.02 | 23.92 | |
| MiMo-V2 FlashModel Variant=Base, # Shots=5-shot, # Activated Params=15B, # Total Params=309B2026.02 | 20.6 |