MoonshotAI
Comparing 2 models from MoonshotAI.
| Model | Total ▼ | Released | Context | CoT | Tooling | Creative Writing | Language | Utility | Reasoning | Text Editing | Rule Following | Hallucination |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MoonshotAI: Kimi K2.6 | 92.31% | Apr 20, 26 | 256k | ✓ | 99.77% | 85.47% | 96.77% | 97.42% | 95.22% | 98.00% | 76.94% | 88.85% |
| MoonshotAI: Kimi K2.5 | 91.04% | Jan 27, 26 | 262k | ✓ | 100.00% | 81.35% | 97.10% | 96.63% | 95.41% | 97.79% | 72.03% | 88.02% |
Model Performance
Cost vs Performance
Compares total benchmark cost against overall score for MoonshotAI models. Quadrant lines are drawn at the median values.
Cost Breakdown
Total benchmark cost per model, broken down by input, reasoning, and output tokens. Toggle between USD and token views.