Comparing 2 models

Claude Opus 4.6 vs GPT-5.6 Luna

Facts first, then task-specific rankings. A highlighted cell is better only for that row, not universally.

metric
Model 1Claude Opus 4.6
Model 2GPT-5.6 Luna
Best for
Vision & Documents (#1)
Code Completion (#1)
Provider
anthropic
openai
Context
1M
1.1MBest
Input / 1M
$5
$0.20Best
Output / 1M
$25
$1.20Best
Tool use
yesBest
yesBest
Vision
yesBest
yesBest
Reasoning
yesBest
yesBest
Open-weight
Released
Aug 26, 2025
Jul 9, 2026

task evidence

How they place when the question changes

Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.