head-to-head

Anthropic: Claude Opus 5 (batch) vs OpenAI: GPT-5.6 Luna

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-23.

Anthropic: Claude Opus 5 (batch) OpenAI: GPT-5.6 Luna
Vendoranthropicopenai
Quality Score100100
Benchmark Score87.362.3
Input Price$2.50/M$0.20/M
Output Price$12.50/M$1.20/M
Context Window1,000,0001,050,000
Max Output128,000128,000
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio--
Benchmark Scores
ai_index83.861.6

Who wins by task?

TaskAnthropic: Claude Opus 5 (batch)OpenAI: GPT-5.6 Luna
SQL Generation 142 141
Code Review 147 143
Code Completion 118 133
Code Refactoring 149 145
Bug Fixing 151 147
Unit Test Generation 134 131
Code Documentation 136 137
Regex Writing 125 125
CI/CD Pipelines 130 127
Frontend Component Design 132 129
Data Analysis 136 133
CSV / Spreadsheet Cleanup 135 136
ETL Scripting 139 136
JSON Extraction 121 131
Bulk Data Labeling 117 129
OCR / Document Parsing 135 134
Table Extraction from PDFs 135 134
Long-Document Summarization 149 147
Short-Form Summarization 117 126
Blog Post Writing 130 129

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Anthropic: Claude Opus 5 (batch) vs Anthropic: Claude Sonnet 5 Anthropic: Claude Opus 5 (batch) vs Anthropic: Claude Sonnet 5 (batch) Anthropic: Claude Opus 5 (batch) vs Google: Gemini 3.5 Flash (batch) Anthropic: Claude Opus 5 (batch) vs Google: Gemini 3.5 Flash Lite Anthropic: Claude Opus 5 (batch) vs Google: Gemini 3.5 Flash Lite (batch) Anthropic: Claude Opus 5 (batch) vs Google: Gemini 3.6 Flash Anthropic: Claude Opus 5 (batch) vs Google: Gemini 3.6 Flash (batch) Anthropic: Claude Opus 5 (batch) vs inclusionAI: Ling 3.0 Flash

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.