GitHub[195K]Try OpenCode

CompareAI models

  1. DeepSeek V4 Flash Vision ExpDeepSeek
  2. Nemotron 3.5 Lightning 30B A3BNvidia
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
DeepSeek V4 Flash Vision Exp100/100No data71/10082/10033/100No data
Nemotron 3.5 Lightning 30B A3B100/100No data87/10064/1000/100No data
Overview
Author
Context length
1M
262K
Reasoning
True
True
Input modalities
Text, Image
Text
Output modalities
Text
Text
Providers
Pricing
Input
$0.22/ 1M
$0.08/ 1M
Output
$0.66/ 1M
$0.20/ 1M
Cached input
$0.007/ 1M
$0.04/ 1M
MomentumLast 2 mo
Unique users
108K
119K
Completed sessions
155,322
863,410
Token share
0.68%
0.43%
Tokens
3T+100%
1.9T+100%
JUL 6AUG 30
JUL 6AUG 30
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.