modelgrep

Anthropic: Claude Opus 4.8 vs Z.ai: GLM 5

Anthropic: Claude Opus 4.8 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
Intelligence Index61.440.6
Coding Index56.739.0
GPQA Diamond92%67%
Design Arena Elo13721313
Speed (tokens/sec)5895
Latency1.8s384ms
Input price /M$5.00$0.600
Output price /M$25.00$1.92
Context window1M203K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON