GitHub[220K]Try 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 placeholder37/10081/10050/10050/100 — Tool calling supported; no comparable benchmark
Hy367/10068/10071/10053/1000/10040/100
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
$0.13/ 1M
Output
$2.70/ 1M
$0.53/ 1M
Cached input
$0.05/ 1M
$0.03/ 1M
MomentumLast 2 mo
Unique users
117K
71K
Completed sessions
2,645,529
509,985
Token share
0.6%
0.02%
Tokens
7.2T+100%
275B-96%
SEP 2OCT 27
SEP 2OCT 27
RetentionWeek 1
Returning users
58.8%2.1K user-weeks
63.9%1.9K user-weeks

Related comparisons. Other model pairs to check.