Z.ai: GLM 5.1 wins on more metrics (8 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Opus 4.5 | Z.ai: GLM 5.1 |
|---|---|---|
| Intelligence Index | 43.1 | 43.8✓ |
| Coding Index | 42.9✓ | 35.8 |
| GPQA Diamond | 81% | 84%✓ |
| Design Arena Elo | 1297 | 1366✓ |
| Speed (tokens/sec) | 57 | 84✓ |
| Latency | 776ms | 475ms✓ |
| Input price /M | $5.00 | $0.980✓ |
| Output price /M | $25.00 | $3.08✓ |
| Context window | 200K | 203K✓ |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSON |