modelgrep

StepFun: Step 3.7 Flash vs Z.ai: GLM 4.7

StepFun: Step 3.7 Flash wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricStepFun: Step 3.7 FlashZ.ai: GLM 4.7
Intelligence Index42.642.1
Coding Index37.136.3
GPQA Diamond81%86%
Design Arena Elo12321274
Speed (tokens/sec)74513
Latency1.8s454ms
Input price /M$0.200$0.400
Output price /M$1.15$1.75
Context window256K203K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON