Try OpenCodeTry OpenCode

Compare AI models: Step 5 Preview vs Hy3

  1. Step 5 PreviewStepFunHollow points use fallbacks · hover for details
  2. Hy3Tencent
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Step 5 Preview50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder38/10079/10050/10050/100 — Tool calling supported; no comparable benchmark
Hy367/10070/10079/10051/1000/10040/100
Overview
Author
Context length
1M
256K
Reasoning
True
True
Input modalities
Text, Image, Video
Text
Output modalities
Text
Text
Providers
Pricing
Input
$1.00/ 1M
$0.07/ 1M
Output
$2.70/ 1M
$0.26/ 1M
Cached input
$0.05/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
134K
53K
Completed sessions
2,695,887
372,158
Token share
0.46%
0.01%
Tokens
7.2T+100%
133B-98%
SEP 26NOV 20
SEP 26NOV 20
RetentionWeek 1
Returning users
59.2%2.3K user-weeks
74.4%892 user-weeks

Related comparisons. Other model pairs to check.