Z.ai: GLM 5.2 wins on more metrics (5 of 8), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | DeepSeek: DeepSeek V4 Pro | Z.ai: GLM 5.2 |
|---|---|---|
| Intelligence Index | 44.3 | 51.1✓ |
| Coding Index | 59.4 | 68.8✓ |
| GPQA Diamond | 89% | 90%✓ |
| Design Arena Elo | 1324✓ | — |
| Speed (tokens/sec) | 56 | 109✓ |
| Latency | 549ms | 509ms✓ |
| Input price /M | $0.435✓ | $0.770 |
| Output price /M | $0.870✓ | $2.42 |
| Context window | 1.0M | 1.0M |
| Capabilities | ReasoningToolsJSON | ReasoningToolsJSON |