modelgrep

Anthropic: Claude Sonnet 4.6 vs Z.ai: GLM 4.7

Z.ai: GLM 4.7 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Sonnet 4.6Z.ai: GLM 4.7
Intelligence Index42.642.1
Coding Index43.036.3
GPQA Diamond80%86%
Design Arena Elo13281274
Speed (tokens/sec)46478
Latency1.1s620ms
Input price /M$3.00$0.400
Output price /M$15.00$1.75
Context window1M203K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON