GPT-5.5 vs GPT-5.6 Luna
Compare GPT-5.5 and GPT-5.6 Luna side-by-side. See how these vision models stack up in Object Detection, Image Captioning, Classification, Open Prompt, and OCR.
Compare GPT-5.5 vs GPT-5.6 Luna live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Detect and compare bounding boxes across models on the same image.
Upload an image
Drag and drop an image here, or click to browse
Models in this comparison
GPT-5.5 vs GPT-5.6 Luna on Vision Evals
GPT-5.5 scores higher on 5 of the six Vision Evals tasks.
The widest gap is Object Detection, where GPT-5.6 Luna leads 61.0% to 43.6%.
Overall, GPT-5.5 averages 74.8% (#16 of 53) against 73.8% (#18 of 53) for GPT-5.6 Luna.
GPT-5.6 Luna is both cheaper ($0.0010 vs $0.022 per sample) and faster (7.4s vs 9.0s per sample).
GPT-5.5 vs GPT-5.6 Luna Comparison Table
Evals updated September 5, 2026Pricing updated September 13, 2026
| Property | GPT-5.5 | GPT-5.6 Luna |
|---|---|---|
| Organization | OpenAI | OpenAI |
| Category | closed | closed |
| Modality | multimodal | multimodal |
| Release Date | Apr 2026 | Jul 2026 |
| Context Window | 1.0M | 1.5M |
| Parameters | ||
| License | Proprietary | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $5.00 | $0.200 |
| Output $/1M | $30.00 | $1.20 |
| Vision Tasks | ||
| Captioning | Demo | Demo |
| Chart Question Answering | ||
| Classification | Demo | Demo |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | Demo |
| OCR | Demo | Demo |
| Vision Language | ||
| Visual Question Answering | Demo | Demo |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort | ||
| Overall | 74.8% | 73.8% |
| Avg cost / sample | $0.022 | $0.0010 |
| Avg speed / sample | 9.03s | 7.38s |
| By task | ||
| Object Detection (low) | 43.6% ±2.2, Mean of 3 runs, range 41.7 to 46.1 | 61.0% ±1.2, Mean of 3 runs, range 59.9 to 62.2 |
| Object Detection (high) | 44.2% ±0.6, Mean of 3 runs, range 43.5 to 44.8 | 62.3% ±1.2, Mean of 3 runs, range 61.4 to 63.8 |
| Counting (low) | 68.0% ±3.4, Mean of 3 runs, range 64.9 to 71.6 | 67.1% ±1.4, Mean of 3 runs, range 66.2 to 68.9 |
| Counting (high) | 68.0% ±1.4, Mean of 3 runs, range 66.2 to 68.9 | 70.7% ±3.4, Mean of 3 runs, range 66.2 to 73.0 |
| Identification (low) | 89.6% ±1.6, Mean of 3 runs, range 87.5 to 90.6 | 83.3% ±1.6, Mean of 3 runs, range 81.3 to 84.4 |
| Identification (high) | 88.5% ±1.6, Mean of 3 runs, range 87.5 to 90.6 | 84.4% ±6.3, Mean of 3 runs, range 78.1 to 90.6 |
| OCR (low) | 91.2% ±0.3, Mean of 3 runs, range 90.9 to 91.6 | 90.7% ±1.8, Mean of 3 runs, range 88.4 to 92.0 |
| OCR (high) | 91.7% ±0.6, Mean of 3 runs, range 91.1 to 92.3 | 91.5% ±0.3, Mean of 3 runs, range 91.2 to 91.7 |
| Data Extraction (low) | 85.9% ±1.5, Mean of 3 runs, range 84.5 to 87.6 | 80.4% ±2.1, Mean of 3 runs, range 78.3 to 82.5 |
| Data Extraction (high) | 86.9% ±0.5, Mean of 3 runs, range 86.6 to 87.6 | 81.8% ±0.5, Mean of 3 runs, range 81.4 to 82.5 |
| Reasoning (low) | 70.6% ±1.0, Mean of 3 runs, range 69.5 to 71.5 | 60.5% ±5.0, Mean of 3 runs, range 55.0 to 64.9 |
| Reasoning (high) | 72.2% ±3.6, Mean of 3 runs, range 68.9 to 76.2 | 65.6% ±3.6, Mean of 3 runs, range 60.9 to 68.2 |
GPT-5.5 vs GPT-5.6 Luna: Overview
GPT-5.5 is a multimodal large language model released by OpenAI on April 23, 2026, engineered for autonomous, multi-step knowledge work and agentic workflows. It accepts text, images, and code as input, featuring enhanced spatial reasoning and visual grounding to support its computer use capabilities for operating software and navigating UI elements. Built to execute complex workflows end-to-end, the model interprets loosely defined tasks, selects appropriate tools, and performs self-verification with minimal user intervention. It is available in a standard version, a Thinking mode for extended reasoning budgets, and a Pro variant that uses parallel test-time compute for maximum precision on complex tasks.
Co-optimized with NVIDIA for GB200 NVL72 infrastructure, GPT-5.5 delivers per-token latency comparable to its predecessor GPT-5.4 while maintaining a 1-million-token context window. Despite increased capability, the model achieves greater token efficiency in coding and data analysis workflows, often completing tasks with fewer total tokens than previous versions. OpenAI reports a 60% reduction in hallucination rate compared to GPT-5.4, improving reliability for accuracy-sensitive applications. API access is available via the Responses and Chat Completions endpoints at $5 per million input tokens and $30 per million output tokens, double the unit price of GPT-5.4.
GPT-5.6 Luna is the fastest and most cost-efficient model in OpenAI's GPT-5.6 family, which also includes Sol (the flagship tier) and Terra (the balanced mid-tier). Introduced under a new naming convention where the generation number (5.6) and a durable capability tier name (Luna, Terra, Sol) together define each model, Luna occupies the lightweight end of the family and is designed for high-volume, latency-sensitive workloads such as summarization, drafting, autocomplete, classification, and routine automation. The GPT-5.6 family as a whole advances capabilities in software engineering, computer use, professional knowledge work, scientific research, and cybersecurity, with all three tiers rated at the "High" capability level under OpenAI's Preparedness Framework for both cybersecurity and biological/chemical risk domains.
GPT-5.6 Luna supports multimodal input and function calling, and shares the family's 1.5 million token context window. On Terminal-Bench 2.1, Luna scores 82.5%, and on the Artificial Analysis Coding Agent Index it outperforms comparable models at roughly one-quarter the estimated cost of higher-tier alternatives. Luna is priced at $1 per million input tokens and $6 per million output tokens, with cached input reads at $0.10 per million tokens under the GPT-5.6 prompt caching scheme, which introduces explicit cache breakpoints and a 30-minute minimum cache life. The model was previewed on June 26, 2026 to a limited group of trusted partners via the OpenAI API and Codex, with general availability rolling out on July 9, 2026 across ChatGPT, Codex, and the API.