Roboflow

GPT-6 Sol vs Mistral Large 4

GPT-6 Sol and Mistral Large 4 score 76.9% vs 56.8% averaged across five Vision Evals tasks (#20 and #51 of 73 models), so GPT-6 Sol leads overall.

  • GPT-6 Sol wins all 5 tasks, with its widest lead on reasoning (72.6% vs 38.9%).
  • Mistral Large 4 is about half the cost: $0.0033 vs $0.0074 overall average cost per sample.
  • GPT-6 Sol is faster: 10.2s vs 31.2s per sample.
OpenAI

Compare GPT-6 Sol vs Mistral Large 4 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.

Open Object Detection in the full playground
OpenAIGPT-6 Sol
Run to compare this model.
MistralMistral Large 4
Run to compare this model.

GPT-6 Sol vs Mistral Large 4 on Vision Evals

Score by taskGPT-6 SolMistral Large 4
Reasoning
72.6
38.9
Counting
76.6
54.5
OCR
66.7
46.1
Object Detection
74.7
59.3
Identification
93.8
85.4

Roboflow Vision Evals. Full breakdown below.

GPT-6 Sol vs Mistral Large 4 Comparison Table

Evals updated November 19, 2026Pricing updated November 22, 2026

PropertyGPT-6 SolMistral Large 4
OrganizationOpenAIMistral
Categoryclosedopen
Modalitymultimodalmultimodal
Release DateSep 2026Oct 2026
Context Window1.1M1.0M
Parametersundisclosed1.05T total, 49B active
LicenseProprietaryCustom
Commercial usecommercial use per vendor termsSee license terms
Pricing per 1M tokens
Input $/1M$2.00$0.700
Output $/1M$10.00$2.10
Vision Tasks
Phrase GroundingNot listedSupported
Promptable Concept SegmentationDemoNot listed
Both support 10 more tasks
Model Features
Both support 3 more features
Vision Evalsground-truth scores across 5 vision tasks, pooled at low effort
Overall
76.9%
56.8%
Avg cost / sample$0.0074$0.0033
Avg speed / sample10.20s31.23s
By task
Object Detection (low)
74.7%
±0.7, Mean of 3 runs, range 74.1 to 75.5
$0.011
59.3%
±0.7, Mean of 3 runs, range 58.5 to 60.0
$0.0028
Object Detection (high)
76.4%
±1.2, Mean of 3 runs, range 75.0 to 77.4
$0.022
50.2%
±2.5, Mean of 3 runs, range 48.0 to 53.0
$0.023
Counting (low)
76.6%
±2.0, Mean of 3 runs, range 74.3 to 78.4
$0.0039
54.5%
±0.7, Mean of 3 runs, range 54.0 to 55.4
$0.0011
Counting (high)
77.5%
±1.3, Mean of 3 runs, range 75.7 to 78.4
$0.0070
63.1%
±2.0, Mean of 3 runs, range 60.8 to 64.9
$0.0095
Identification (low)
93.8%
±0.0, Mean of 3 runs, range 93.8 to 93.8
$0.0027
85.4%
±3.1, Mean of 3 runs, range 81.3 to 87.5
$0.0009
Identification (high)
92.7%
±1.6, Mean of 3 runs, range 90.6 to 93.8
$0.0036
85.4%
±1.6, Mean of 3 runs, range 84.4 to 87.5
$0.0044
OCR (low)
66.7%
$0.0077
46.1%
$0.0044
by category
Single value
45.6%
Transcription
88.3%
Structured JSON
83.4%
Text localization
65.7%
Single value
33.5%
Transcription
68.9%
Structured JSON
71.7%
Text localization
0.0%
OCR (high)
68.8%
$0.018
54.5%
$0.021
by category
Single value
47.4%
Transcription
91.0%
Structured JSON
85.3%
Text localization
68.7%
Single value
38.3%
Transcription
75.3%
Structured JSON
76.4%
Text localization
28.8%
Reasoning (low)
72.6%
±3.6, Mean of 3 runs, range 69.5 to 76.8
$0.0037
38.9%
±0.3, Mean of 3 runs, range 38.4 to 39.1
$0.0013
Reasoning (high)
77.7%
±1.0, Mean of 3 runs, range 76.8 to 78.8
$0.0061
57.6%
±2.0, Mean of 3 runs, range 55.6 to 59.6
$0.013

GPT-6 Sol vs Mistral Large 4: Overview

GPT-6 Sol

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. Its vision behavior covers image understanding tasks such as visual question answering, captioning, document and chart interpretation, and text recognition.

Mistral Large 4

Mistral Large 4, nicknamed Le Chonk, is a natively multimodal mixture-of-experts model from Mistral that accepts interleaved text and image input and produces text output. It uses a granular MoE design with roughly 1.05 trillion total parameters and 49 billion active per token, reported as 52 billion when embeddings and output layers are counted, paired with a 1.6 billion parameter vision encoder and a context window of one million tokens. The model is trained from scratch on about 3,800 NVIDIA Grace Blackwell GPUs in Mistral's European data centers and supports more than 160 languages. It behaves as a hybrid instruct and reasoning system, with a reasoning effort setting that selects between direct answers and longer deliberation, alongside function calling and structured output for agentic workflows.

Image understanding is a focus of this generation, covering documents, charts, technical drawings and natural scenes, and the model emits bounding box coordinates for visual grounding queries. Reported grounding results include 42 percent on Dense200 and 73 percent on the DIOR-RSVG remote sensing benchmark. Mistral describes agentic vision workflows in which the model zooms into gigapixel satellite imagery or engineering drawings to verify details, and reports coding results such as 62 percent on DeepSWE. Figures published at preview time are preliminary because the reinforcement learning phase is still in progress.