Z.ai: GLM 4.7 Flash wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Qwen: Qwen3 235B A22B Thinking 2507 | Z.ai: GLM 4.7 Flash |
|---|---|---|
| Intelligence Index | 29.5 | 30.1✓ |
| Coding Index | 23.2 | 25.9✓ |
| GPQA Diamond | 79%✓ | 58% |
| Design Arena Elo | 1097 | 1265✓ |
| Speed (tokens/sec) | 68✓ | 35 |
| Latency | 350ms | 308ms✓ |
| Input price /M | $0.100 | $0.060✓ |
| Output price /M | $0.100✓ | $0.400 |
| Context window | 262K✓ | 203K |
| Capabilities | ReasoningToolsJSON | ReasoningToolsJSON |