GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 ProDeepSeek
  2. Llama 4 Scout 17B InstructMeta
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Pro100/10087/10051/10081/1000/10044/100
Llama 4 Scout 17B Instruct0/100No data70/100100/10033/100No data
Overview
Author
Context length
1M
10M
Reasoning
True
False
Input modalities
Text
Text, Image
Output modalities
Text
Text
Providers
Pricing
Input
$0.66/ 1M
$0.18/ 1M
Output
$1.98/ 1M
$0.59/ 1M
Cached input
$0.02/ 1M
Unknown
MomentumLast 2 mo
Unique users
1.3M
No usage
Completed sessions
2,222,390
No usage
Token share
3.76%
No usage
Tokens
24T-11%
No usage
JUL 23SEP 16
No trend data
RetentionWeek 1
Returning users
61.9%118K user-weeks
Pending

Related comparisons. Other model pairs to check.