modelgrep

Anthropic: Claude Fable 5 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 Fable 5Z.ai: GLM 5.2
Intelligence Index59.950.7
Coding Index62.050.7
GPQA Diamond93%90%
Design Arena Elo14151369
Speed (tokens/sec)33
Latency1.7s
Input price /M$10.00$1.40
Output price /M$50.00$4.40
Context window1M1.0M
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON