GitHub[195K]Try OpenCode

CompareAI models

  1. Claude Opus 5Anthropic
  2. Sonar Deep ResearchPerplexity
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Claude Opus 5100/100100/1008/10081/10050/100No data
Sonar Deep Research100/100No data25/10018/1000/100No data
Overview
Author
Context length
1M
128K
Reasoning
True
True
Input modalities
Text, Image, Pdf
Text
Output modalities
Text
Text
Providers
Pricing
Input
$5.00/ 1M
$2.00/ 1M
Output
$25/ 1M
$8.00/ 1M
Cached input
$0.50/ 1M
Unknown
MomentumLast 2 mo
Unique users
0
No usage
Completed sessions
1
No usage
Token share
0%
No usage
Tokens
00%
No usage
No trend data
No trend data
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.