GitHub[208K]Try OpenCode

Compare AI models: DeepSeek V4 Pro 0813 vs Step 5 Preview

  1. DeepSeek V4 Pro 0813DeepSeek
  2. Step 5 PreviewStepFunHollow points use fallbacks · hover for details
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro 081378/100100/10033/10082/1000/10050/100
Step 5 Preview50/100 — Reasoning supported; no comparable benchmark50/100 — No data; neutral placeholder39/10082/10050/10050/100 — Tool calling supported; no comparable benchmark
Overview
Author
Context length
1M
1M
Reasoning
True
True
Input modalities
Text
Text, Image, Video
Output modalities
Text
Text
Providers
Pricing
Input
$1.32/ 1M
$0.96/ 1M
Output
$3.96/ 1M
$2.74/ 1M
Cached input
$0.04/ 1M
$0.05/ 1M
MomentumLast 2 mo
Unique users
26
90K
Completed sessions
422
2,291,249
Token share
0%
0.63%
Tokens
72M+100%
6.3T+100%
AUG 21OCT 15
AUG 21OCT 15
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.