modelgrep

MoonshotAI: Kimi K2.5 vs StepFun: Step 3.5 Flash

StepFun: Step 3.5 Flash wins on more metrics (5 of 8), but the right pick depends on what you optimize for — see the breakdown below.

MetricMoonshotAI: Kimi K2.5StepFun: Step 3.5 Flash
Intelligence Index37.337.8
Coding Index25.831.6
GPQA Diamond79%83%
Design Arena Elo1293
Speed (tokens/sec)8947
Latency211ms403ms
Input price /M$0.375$0.090
Output price /M$2.02$0.300
Context window262K262K
CapabilitiesReasoningToolsJSONVisionReasoningToolsJSON