Roboflow

Not available to run yet

GPT-6 Sol is on the Vision Evals leaderboard. Running it in the Playground is not available yet. View evals

GPT-6 Sol Overview

GPT-6 Sol is a proprietary multimodal reasoning model from OpenAI, released on September 22, 2026 alongside GPT-6 Luna as an efficiency-oriented tier of the GPT-6 family that began with GPT-6 Astra. OpenAI states that Sol and Luna are trained with methods similar to those used for Astra, carrying the same work on professional tasks, factuality, coding, computer use, and alignment into models that run faster. Sol accepts text and image input and returns text output, and OpenAI documents a context window of roughly one million tokens together with a knowledge cutoff of April 20, 2026.

The model targets complex coding and agentic workflows and exposes a configurable reasoning effort setting with levels of none, low, medium, high, xhigh, and max, which trades latency and token consumption against answer quality. OpenAI reports results including 33.2% on AutomationBench at xhigh effort and 56.4% on Agents' Last Exam at max effort, while its reported DeepSWE and OSWorld 2.0 figures of 68.8% and 64.4% fall below those of the earlier GPT-5.6 Sol. Its vision behavior covers image understanding tasks such as visual question answering, captioning, document and chart interpretation, and text recognition.

GPT-6 Sol Details & Performance

Details

Resources

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRVision LanguageVisual Question AnsweringObject Detection

Features

Foundation VisionLLMs with Vision CapabilitiesMultimodal Vision

Usage

Past 30 Days

Not available

Not in Playground

Performance

Avg. Latency

GPT-6 Sol Vision Evals

Vision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across six vision tasks, and answers are scored against ground truth.

Evals updated September 22, 2026Pricing updated September 22, 2026

Overall score#10 of 57
80.7%
Avg cost / sample#38 of 57
$0.0065
Avg speed / sample#24 of 57
8.15s
Avg tokens / sample
1.9K

Strengths and weaknesses

GPT-6 Sol averages 80.7% across the six Vision Evals tasks, ranking #10 of 57 models overall.

Its weakest relative showing is Data Extraction, ranking #39 of 57 at 80.4%.

At $0.0065 per sample it is the 38th cheapest of the 57 benchmarked models, and its average inference time of 8.1s per sample makes it the 24th fastest.

Performance profile

Field medianGPT-6 Sol

Field medians: Object Detection 54.3%, Counting 61.7%, Identification 84.4%, OCR 88.7%, Data Extraction 84.5%, Reasoning 54.8%.

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection (low)
73.6%
±0.6, Mean of 3 runs, range 72.9 to 74.2
#4 of 57$0.0119.08s
Object Detection (high)
75.2%
±0.9, Mean of 3 runs, range 74.1 to 75.9
#4 of 23$0.02220.89s
Counting (low)
74.8%
±2.7, Mean of 3 runs, range 71.6 to 77.0
#10 of 57$0.00397.31s
Counting (high)
76.1%
±3.4, Mean of 3 runs, range 71.6 to 78.4
#8 of 23$0.007112.51s
Identification (low)
91.7%
±3.1, Mean of 3 runs, range 87.5 to 93.8
#12 of 57$0.00275.32s
Identification (high)
92.7%
±1.6, Mean of 3 runs, range 90.6 to 93.8
#7 of 23$0.00366.38s
OCR (low)
91.7%
±0.4, Mean of 3 runs, range 91.3 to 92.1
#16 of 57$0.00707.25s
OCR (high)
91.9%
±0.3, Mean of 3 runs, range 91.6 to 92.2
#6 of 23$0.01919.70s
Data Extraction (low)
80.4%
±0.0, Mean of 3 runs, range 80.4 to 80.4
#39 of 57$0.00315.68s
Data Extraction (high)
82.5%
±1.0, Mean of 3 runs, range 81.4 to 83.5
#17 of 23$0.00457.76s
Reasoning (low)
72.2%
±1.7, Mean of 3 runs, range 70.9 to 74.2
#11 of 57$0.00399.41s
Reasoning (high)
77.9%
±2.6, Mean of 3 runs, range 75.5 to 80.8
#8 of 43$0.006910.44s
  • Thinking longer helps: 1.6 points higher on object detection at high effort for 2.1x the cost and 2.3x the latency.
  • Thinking longer helps: 1.4 points higher on counting at high effort for 1.8x the cost and 1.7x the latency.
  • Thinking longer helps: 1 points higher on identification at high effort for 1.3x the cost and 1.2x the latency.
  • Thinking longer helps: 0.2 points higher on ocr at high effort for 2.7x the cost and 2.7x the latency.
  • Thinking longer helps: 2.1 points higher on data extraction at high effort for 1.4x the cost and 1.4x the latency.
  • Thinking longer helps: 5.7 points higher on reasoning at high effort for 1.8x the cost and 1.1x the latency.

Price vs. performance

Score vs. cost

Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.

56 models on the current benchmark · scores and efficiency pooled across all six tasks at low effort · GPT-6 Sol highlighted

GPT-6 Sol scores are the mean of 3 runs per task at both low and high effort · Methodology

View all Vision Evals →

GPT-6 Sol Pricing

GPT-6 Sol costs $2.00 per 1M input tokens and $10.00 per 1M output tokens.

Input$2.00 / 1M tokens
Output$10.00 / 1M tokens
Cached input$0.200 / 1M tokens

Pricing updated Sep 22, 2026

Other OpenAI GPT models

Other versions in the same family as GPT-6 Sol.

GPT-6 Sol License

Proprietary

GPT-6 Sol is proprietary: the weights are not distributed, and the GPT-6 Sol license is the vendor's commercial terms of service that you accept when you call the API.

Commercial use
Permitted under the vendor terms, typically metered per token or per request, with the vendor usage policy applying to your inputs and outputs.
Modification
Not available. GPT-6 Sol weights are closed, so you can configure prompts and use vendor-hosted fine-tuning where it is offered, but you cannot modify the model itself.
Redistribution
Not permitted. You cannot self-host or resell the model; you build on the hosted API instead.

Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.

Do I need a commercial license for GPT-6 Sol?

Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy a model whose commercial license is included in your plan — on Roboflow Managed Cloud or a Self-Hosted Inference Server — Roboflow's licensing page lists the supported alternatives to GPT-6 Sol.

Do not hesitate to reach out with questions for your commercial project — our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.

Talk to sales

This model is proprietary. The author retains all rights, and use of the model is governed by their specific terms of service or license agreement.

Commercial use depends on the terms set by the model author. Most proprietary commercial models require a paid subscription, API key, or per-call billing. Check the provider’s pricing and terms-of-service for details.

License information is provided as a guide and is not legal advice.

Frequently Asked Questions About GPT-6 Sol Vision

Yes. GPT-6 Sol accepts image input and handles OCR, data extraction, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Object Detection at 73.6% (#4 of 57 at low effort).

Yes, and it is one of the model's strongest vision skills: its transcriptions match the ground truth 91.7% on average (#16 of 57 at low effort) on Vision Evals OCR. Pulling specific fields out of documents (data extraction) scores 80.4%.

It's serviceable. On Vision Evals, GPT-6 Sol scores 73.6% mAP@50 on object detection (#4 of 57 at low effort) and 74.8% judge-graded accuracy on object counting.

On our benchmark's task mix, GPT-6 Sol averages $0.0065 per sample at $2.00 per 1M input and $10.00 per 1M output tokens (#38 of 57 on cost), with an average speed of 8.1s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, GPT-6 Sol sits #10 of 57 at 80.7%, just behind Claude Fable 5.1 (81.3%) and just ahead of Muse Spark 1.1 (80.5%). See the full side-by-side: GPT-6 Sol vs Claude Fable 5.1.