GPT-5.6 Luna vs Grok 4.7
Compare GPT-5.6 Luna and Grok 4.7 side-by-side.
Compare GPT-5.6 Luna vs Grok 4.7 live
Run the same image across every model that supports a task and compare their outputs side-by-side.
These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.
Models in this comparison
GPT-5.6 Luna vs Grok 4.7 on Vision Evals
Grok 4.7 scores higher on 4 of the six Vision Evals tasks.
The widest gap is Object Detection, where GPT-5.6 Luna leads 61.0% to 40.4%.
Overall, GPT-5.6 Luna averages 73.8% (#18 of 54) against 71.9% (#22 of 54) for Grok 4.7.
GPT-5.6 Luna is both cheaper ($0.0010 vs $0.012 per sample) and faster (7.4s vs 23.6s per sample).
GPT-5.6 Luna vs Grok 4.7 Comparison Table
Evals updated September 22, 2026Pricing updated September 22, 2026
| Property | GPT-5.6 Luna | Grok 4.7 |
|---|---|---|
| Organization | OpenAI | SpaceXAI |
| Category | closed | closed |
| Modality | multimodal | — |
| Release Date | Jul 2026 | Sep 2026 |
| Context Window | 1.5M | 500K |
| Parameters | ||
| License | Proprietary | Proprietary |
| Pricing per 1M tokens | ||
| Input $/1M | $0.200 | $1.60 |
| Output $/1M | $1.20 | $4.80 |
| Vision Tasks | ||
| Captioning | Demo | |
| Chart Question Answering | ||
| Classification | Demo | |
| Document Question Answering | ||
| Image Tagging | ||
| Multi-Label Classification | ||
| Object Detection | Demo | |
| OCR | Demo | |
| Vision Language | ||
| Visual Question Answering | Demo | |
| Model Features | ||
| Foundation Vision | ||
| LLMs with Vision Capabilities | ||
| Multimodal Vision | ||
Vision Evalsground-truth scores across 6 vision tasks, pooled at low effort | ||
| Overall | 73.8% | 71.9% |
| Avg cost / sample | $0.0010 | $0.012 |
| Avg speed / sample | 7.38s | 23.55s |
| By task | ||
| Object Detection (low) | 61.0% ±1.2, Mean of 3 runs, range 59.9 to 62.2 | 40.4% ±0.6, Mean of 3 runs, range 39.8 to 41.0 |
| Object Detection (high) | 62.3% ±1.2, Mean of 3 runs, range 61.4 to 63.8 | 41.2% ±1.6, Mean of 3 runs, range 39.6 to 42.8 |
| Counting (low) | 67.1% ±1.4, Mean of 3 runs, range 66.2 to 68.9 | 61.7% ±1.3, Mean of 3 runs, range 60.8 to 63.5 |
| Counting (high) | 70.7% ±3.4, Mean of 3 runs, range 66.2 to 73.0 | 60.8% ±1.3, Mean of 3 runs, range 59.5 to 62.2 |
| Identification (low) | 83.3% ±1.6, Mean of 3 runs, range 81.3 to 84.4 | 87.5% ±3.1, Mean of 3 runs, range 84.4 to 90.6 |
| Identification (high) | 84.4% ±6.3, Mean of 3 runs, range 78.1 to 90.6 | 80.2% ±1.6, Mean of 3 runs, range 78.1 to 81.3 |
| OCR (low) | 90.7% ±1.8, Mean of 3 runs, range 88.4 to 92.0 | 92.6% ±0.7, Mean of 3 runs, range 92.1 to 93.4 |
| OCR (high) | 91.5% ±0.3, Mean of 3 runs, range 91.2 to 91.7 | 93.5% ±0.3, Mean of 3 runs, range 93.1 to 93.8 |
| Data Extraction (low) | 80.4% ±2.1, Mean of 3 runs, range 78.3 to 82.5 | 84.9% ±2.6, Mean of 3 runs, range 82.5 to 87.6 |
| Data Extraction (high) | 81.8% ±0.5, Mean of 3 runs, range 81.4 to 82.5 | 87.6% ±1.5, Mean of 3 runs, range 86.6 to 89.7 |
| Reasoning (low) | 60.5% ±5.0, Mean of 3 runs, range 55.0 to 64.9 | 64.2% ±2.3, Mean of 3 runs, range 62.3 to 66.9 |
| Reasoning (high) | 65.6% ±3.6, Mean of 3 runs, range 60.9 to 68.2 | 66.9% ±1.3, Mean of 3 runs, range 65.6 to 68.2 |
GPT-5.6 Luna vs Grok 4.7: Overview
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.
Grok 4.7 is a proprietary model from SpaceXAI, released on September 21, 2026. It accepts text and images as input and returns text. It extends Grok 4.6 and is listed at the same API price.
Its Vision Evals scores are on the leaderboard. Running it in the Playground is not available yet, because the inference workflow is not ready.
Frequently Asked Questions
On Roboflow's Vision Evals, Grok 4.7 performed better. It scores higher on 4 of the six vision tasks and averages 71.9% (#22 of 54) against 73.8% (#18 of 54) for GPT-5.6 Luna. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.
Yes. On the Vision Evals Object Detection benchmark at low effort, GPT-5.6 Luna leads with 61.0% against 40.4%. This is the widest gap between the two models across the benchmark's tasks.
GPT-5.6 Luna is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0010 per sample against $0.012. GPT-5.6 Luna is priced at $0.20 per 1M input tokens and $1.20 per 1M output; Grok 4.7 is priced at $1.60 per 1M input tokens and $4.80 per 1M output. Actual costs depend on your image sizes, prompts, and output length.
GPT-5.6 Luna is faster. Across Roboflow's Vision Evals it averaged 7.4s per inference against 23.6s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.