modelgrep

Anthropic: Claude Opus 4.8 vs Z.ai: GLM 5.2

Z.ai: GLM 5.2 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricAnthropic: Claude Opus 4.8Z.ai: GLM 5.2
Intelligence Index55.750.7
Coding Index56.750.7
GPQA Diamond92%90%
Design Arena Elo13731369
Speed (tokens/sec)33
Latency1.7s
Input price /M$5.00$1.40
Output price /M$25.00$4.40
Context window1M1.0M
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON