modelgrep

StepFun: Step 3.7 Flash vs Tencent: Hy3 preview

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 FlashTencent: Hy3 preview
Intelligence Index42.641.9
Coding Index37.136.5
GPQA Diamond81%87%
Design Arena Elo1232
Speed (tokens/sec)8261
Latency1.5s3.5s
Input price /M$0.200$0.063
Output price /M$1.15$0.210
Context window256K262K
CapabilitiesReasoningToolsJSONVisionReasoningTools