Roboflow

GPT-5.6 Terra vs Mistral Large 4

GPT-5.6 Terra and Mistral Large 4 score 66.0% vs 56.8% averaged across five Vision Evals tasks (#36 and #51 of 73 models), so GPT-5.6 Terra leads overall.

  • GPT-5.6 Terra wins all 5 tasks, with its widest lead on reasoning (60.9% vs 38.9%).
  • Mistral Large 4 is about a third of the cost: $0.0033 vs $0.010 overall average cost per sample.
  • GPT-5.6 Terra is faster: 9.5s vs 31.2s per sample.

Compare GPT-5.6 Terra 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-5.6 Terra
Run to compare this model.
MistralMistral Large 4
Run to compare this model.

GPT-5.6 Terra vs Mistral Large 4 on Vision Evals

Score by taskGPT-5.6 TerraMistral Large 4
Reasoning
60.9
38.9
Counting
65.8
54.5
OCR
56.3
46.1
Object Detection
60.6
59.3
Identification
86.5
85.4

Roboflow Vision Evals. Full breakdown below.

GPT-5.6 Terra vs Mistral Large 4 Comparison Table

Evals updated November 19, 2026Pricing updated November 21, 2026

PropertyGPT-5.6 TerraMistral Large 4
OrganizationOpenAIMistral
Categoryclosedopen
Modalitymultimodalmultimodal
Release DateJul 2026Oct 2026
Context Window1.1M1.0M
ParametersUnknown1.05T total, 49B active
LicenseProprietaryCustom
Commercial usecommercial use per vendor termsSee license terms
Pricing per 1M tokens
Input $/1M$2.00$0.700
Output $/1M$12.00$2.10
Vision Tasks
Phrase GroundingNot listedSupported
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
66.0%
56.8%
Avg cost / sample$0.010$0.0033
Avg speed / sample9.52s31.23s
By task
Object Detection (low)
60.6%
±0.2, Mean of 3 runs, range 60.3 to 60.7
$0.014
59.3%
±0.7, Mean of 3 runs, range 58.5 to 60.0
$0.0028
Object Detection (high)
61.3%
±0.4, Mean of 3 runs, range 60.8 to 61.6
$0.026
50.2%
±2.5, Mean of 3 runs, range 48.0 to 53.0
$0.023
Counting (low)
65.8%
±2.0, Mean of 3 runs, range 63.5 to 67.6
$0.0056
54.5%
±0.7, Mean of 3 runs, range 54.0 to 55.4
$0.0011
Counting (high)
62.6%
±2.7, Mean of 3 runs, range 59.5 to 64.9
$0.0076
63.1%
±2.0, Mean of 3 runs, range 60.8 to 64.9
$0.0095
Identification (low)
86.5%
±1.6, Mean of 3 runs, range 84.4 to 87.5
$0.0034
85.4%
±3.1, Mean of 3 runs, range 81.3 to 87.5
$0.0009
Identification (high)
86.5%
±3.1, Mean of 3 runs, range 84.4 to 90.6
$0.0038
85.4%
±1.6, Mean of 3 runs, range 84.4 to 87.5
$0.0044
OCR (low)
56.3%
$0.011
46.1%
$0.0044
by category
Single value
36.1%
Transcription
79.9%
Structured JSON
76.8%
Text localization
42.3%
Single value
33.5%
Transcription
68.9%
Structured JSON
71.7%
Text localization
0.0%
OCR (high)
56.9%
$0.021
54.5%
$0.021
by category
Single value
37.4%
Transcription
80.2%
Structured JSON
77.3%
Text localization
41.9%
Single value
38.3%
Transcription
75.3%
Structured JSON
76.4%
Text localization
28.8%
Reasoning (low)
60.9%
±2.0, Mean of 3 runs, range 59.6 to 63.6
$0.0051
38.9%
±0.3, Mean of 3 runs, range 38.4 to 39.1
$0.0013
Reasoning (high)
65.3%
±1.0, Mean of 3 runs, range 64.2 to 66.2
$0.0067
57.6%
±2.0, Mean of 3 runs, range 55.6 to 59.6
$0.013

GPT-5.6 Terra vs Mistral Large 4: Overview

GPT-5.6 Terra

GPT-5.6 Terra is the mid-tier reasoning model in OpenAI's GPT-5.6 family, which also includes the flagship Sol and the lightweight Luna. Introduced in a limited preview on June 26, 2026, and made broadly available on July 9, 2026, Terra accepts text and image input and produces text output, supporting vision, function calling, tool use, and agentic workflows. It is designed as a balanced option for everyday professional and production workloads — including coding assistance, document analysis, customer support, and multi-step agent tasks — where both output quality and cost efficiency matter. OpenAI positions Terra as delivering performance competitive with GPT-5.5 at approximately half the price, with a context window of around 1,050,000 tokens. Under OpenAI's Preparedness Framework, Terra is rated High for cybersecurity and biological capabilities, meaning it demonstrates meaningful capability in those domains without reaching the Critical threshold.

GPT-5.6 introduces a new naming convention in which the generation number (5.6) is paired with a durable capability tier name (Sol, Terra, or Luna), allowing each tier to advance on its own schedule. Terra carries the API identifier gpt-5.6-terra and supports the same reasoning effort controls available across the family, including adjustable reasoning depth. The model includes prompt caching with explicit cache breakpoints and a 30-minute minimum cache life, with cache writes billed at 1.25x the uncached input rate and cache reads receiving a 90% discount. GPT-5.6 Terra is a proprietary, closed-weights model served through the OpenAI API, Codex, and ChatGPT.

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.

Frequently Asked Questions

On Roboflow's Vision Evals, GPT-5.6 Terra performed better. It scores higher on all five vision tasks and averages 66.0% (#36 of 73) against 56.8% (#51 of 73) for Mistral Large 4. These scores measure vision capabilities only; either model may perform differently on work outside this benchmark's tasks.

Yes. On the Vision Evals Reasoning benchmark at low effort, GPT-5.6 Terra leads with 60.9% against 38.9%. This is the widest gap between the two models across the benchmark's tasks.

Mistral Large 4 is cheaper to run. Across Roboflow's Vision Evals task mix it averaged $0.0033 per sample against $0.010. GPT-5.6 Terra is priced at $2.00 per 1M input tokens and $12.00 per 1M output; Mistral Large 4 is priced at $0.70 per 1M input tokens and $2.10 per 1M output. Actual costs depend on your image sizes, prompts, and output length.

GPT-5.6 Terra is faster. Across Roboflow's Vision Evals it averaged 9.5s per inference against 31.2s. Latency varies with image size, prompt length, and provider load, so treat these as relative rather than guaranteed figures.

Yes. The comparison demo on this page runs both models on the same image side by side for image classification and open prompts in the free Roboflow Playground. You can try it instantly, and a free account gives you more runs with free Roboflow credits.