GitHub[195K]Try OpenCode

CompareAI models

  1. test-perplexity-claude-sonnet-4-5-20250929Anthropic
  2. Grok 4.5xAI
ReasoningCodingCost efficiencyContext windowMultimodalTool use
Normalized model capability scores
ModelReasoningCodingCost efficiencyContext windowMultimodalTool use
test-perplexity-claude-sonnet-4-5-20250929No dataNo dataNo dataNo dataNo dataNo data
Grok 4.5100/100100/10029/10075/10033/10062/100
Overview
Author
Context length
Unknown
500K
Reasoning
Unknown
True
Input modalities
Unknown
Text, Image
Output modalities
Unknown
Text
Providers
Pricing
Input
Unknown
$2.00/ 1M
Output
Unknown
$6.00/ 1M
Cached input
Unknown
$0.30/ 1M
MomentumLast 2 mo
Unique users
1
128K
Completed sessions
1
106,154
Token share
0%
0.03%
Tokens
1.7M+100%
123B+100%
JUL 8SEP 1
JUL 8SEP 1
RetentionWeek 1
Returning users
Pending
47.3%4.8K user-weeks

Related comparisons. Other model pairs to check.