Claude Opus 5 vs GPT-5.6 Luna: Release Comparison
Comparison of the Claude Opus 5 and GPT-5.6 Luna releases: 5 and 6 models respectively, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across all 11 models.
- For intelligence, Claude Opus 5 scores highest: Claude Opus 5 (Adaptive Reasoning, Max Effort) at 51, against GPT-5.6 Luna (max) at 38 for GPT-5.6 Luna.
- For output speed, GPT-5.6 Luna is fastest: GPT-5.6 Luna (xhigh) at 122 t/s, against Claude Opus 5 (Adaptive Reasoning, Low Effort) at 54 t/s for Claude Opus 5.
- For cost per task, GPT-5.6 Luna is cheapest: GPT-5.6 Luna (low) at $0.01, against Claude Opus 5 (Adaptive Reasoning, Low Effort) at $1.10 for Claude Opus 5.
Releases compared
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indices
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2, AA-Briefcase, Terminal-Bench v4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2, AA-Briefcase, AA-LCR v1.1 · Higher is better
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 (Adaptive Reasoning, Max Effort) |  Anthropic | 51 | - | 1M | $3.9 | 53 | Not available |   | |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 50 | - | 1M | $3.9 | 53 | Not available | | |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 48 | - | 1M | $3.9 | 52 | Not available | | |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 45 | - | 1M | $3.9 | 52 | Not available | | |
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 40 | - | 1M | $3.9 | 54 | Not available | | |
| GPT-5.6 Luna (max) |  OpenAI | 38 | - | 1M | $0.2 | 121 | Not available | | |
| GPT-5.6 Luna (xhigh) | OpenAI | 35 | - | 1M | $0.2 | 122 | Not available |  | |
| GPT-5.6 Luna (high) | OpenAI | 32 | - | 1M | $0.2 | 101 | Not available | | |
| GPT-5.6 Luna (medium) | OpenAI | 25 | - | 1M | $0.2 | 105 | Not available | | |
| GPT-5.6 Luna (low) | OpenAI | 22 | - | 1M | $0.2 | 107 | Not available | | |
| GPT-5.6 Luna (Non-reasoning) | OpenAI | 17 | - | 1M | $0.2 | 107 | Not available | |