Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Moonshot AI | Z.AI |
|---|---|---|
| Params | 2.8T / 104B | 754B |
| Architecture | moe | moe |
| Context | 1M | 205K |
| Weights | ||
| License | Custom licence | MIT License |
| 1752.7 GBest | 475.3 GBest | |
| Cheapest hosted (out/1M) | $15.00 · Novita AI | $2.55 · OpenRouter |
| Released | Jun 13, 2026 | Feb 11, 2026 |
| LiveBench | 79.2 | — |
| LiveBench Agentic Coding | 62.2 | — |
| LiveBench Coding | 81.5 | — |
| LiveBench Data Analysis | 78.7 | — |
| LiveBench Instruction Following | 71.4 | — |
| LiveBench Language | 85.5 | — |
| LiveBench Mathematics | 84.4 | — |
| LiveBench Reasoning | 90.7 | — |
| Arena Agent (IPS) | 0.099via Max | — |
| Arena Coding | 1531.5via Max | 1497.4 |
| Arena Creative Writing | 1468.8via Max | 1446.2 |
| Arena Hard Prompts | 1505.5via Max | 1477.9 |
| Arena Instruction Following | 1479.7via Max | 1446.6 |
| Arena Text (overall) | 1485.3via Max | 1456.7 |
| Arena Code (WebDev) | 1675.6via Max | 1434.7 |
| Arena Maths | — | 1442.3 |
| SWE-bench Verified | — | 72.8via mini-SWE-agent |
