modelgrep

Qwen: Qwen3 235B A22B Thinking 2507 vs Z.ai: GLM 4.7 Flash

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.

MetricQwen: Qwen3 235B A22B Thinking 2507Z.ai: GLM 4.7 Flash
Intelligence Index29.530.1
Coding Index23.225.9
GPQA Diamond79%58%
Design Arena Elo10971265
Speed (tokens/sec)6835
Latency350ms308ms
Input price /M$0.100$0.060
Output price /M$0.100$0.400
Context window262K203K
CapabilitiesReasoningToolsJSONReasoningToolsJSON