Z.ai: GLM 5.2 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | NVIDIA: Nemotron 3 Ultra | Z.ai: GLM 5.2 |
|---|---|---|
| Intelligence Index | 37.8 | 51.1✓ |
| Coding Index | 49.3 | 68.8✓ |
| GPQA Diamond | 87% | 90%✓ |
| Design Arena Elo | 1202 | 1371✓ |
| Speed (tokens/sec) | 77✓ | 46 |
| Latency | 352ms✓ | 1.5s |
| Input price /M | $0.500✓ | $1.20 |
| Output price /M | $2.20✓ | $4.10 |
| Context window | 1M | 1.0M✓ |
| Capabilities | ReasoningToolsJSON | ReasoningToolsJSON |