GitHub[195K]Try OpenCode

CompareAI models

  1. Mistral Medium 3.5Mistral
  2. Sonar Deep ResearchPerplexity
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
Mistral Medium 3.5100/10065/10028/10064/10033/100No data
Sonar Deep Research100/100No data25/10019/1000/100No data
Overview
Author
Context length
262K
128K
Reasoning
True
True
Input modalities
Text, Image
Text
Output modalities
Text
Text
Providers
Pricing
Input
$1.50/ 1M
$2.00/ 1M
Output
$7.50/ 1M
$8.00/ 1M
Cached input
Unknown
Unknown
MomentumLast 2 mo
Unique users
No usage
No usage
Completed sessions
No usage
No usage
Token share
No usage
No usage
Tokens
No usage
No usage
No trend data
No trend data
RetentionWeek 1
Returning users
Pending
Pending

Related comparisons. Other model pairs to check.