Roboflow

GPT-5.6 Luna vs Qwen3.5 9b

GPT-5.6 Luna averages 64.7% across five Vision Evals tasks and Qwen3.5 9b 56.0% across four (#39 and #52 of 73 models), so GPT-5.6 Luna leads overall.

  • GPT-5.6 Luna wins 3 of the 4 tasks both ran, with its widest lead on object detection (61.0% vs 38.1%).
  • GPT-5.6 Luna is about half the cost: $0.0011 vs $0.0021 overall average cost per sample.
  • GPT-5.6 Luna is faster: 8.6s vs 41.4s per sample.

Compare GPT-5.6 Luna vs Qwen3.5 9b live

Run the same image across every model that supports a task and compare their outputs side-by-side.

Extract and compare text from images across multiple models.

Open OCR in the full playground
OpenAIGPT-5.6 Luna
Run to compare this model.
QwenQwen3.5 9b
Run to compare this model.

GPT-5.6 Luna vs Qwen3.5 9b on Vision Evals

Score by taskGPT-5.6 LunaQwen3.5 9b
Object Detection
61.0
38.1
Reasoning
60.5
45.9
Counting
67.1
56.8
Identification
83.3
83.3

Roboflow Vision Evals. Full breakdown below.

GPT-5.6 Luna vs Qwen3.5 9b Comparison Table

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

PropertyGPT-5.6 LunaQwen3.5 9b
OrganizationOpenAIQwen
Categoryclosedopen
Modalitymultimodalmultimodal
Release DateJul 2026Mar 2026
Context Window1.5M262K
ParametersUnknown9B
LicenseProprietaryApache 2.0
Commercial usecommercial use per vendor termsfree for commercial use
Pricing per 1M tokens
Input $/1M$0.200$0.170
Output $/1M$1.20$0.250
Vision Tasks
ClassificationDemoSupported
Object DetectionDemoSupported
Both support 8 more tasks
Model Features
Both support 3 more features
Vision Evalsground-truth scores across 5 vision tasks, pooled at low effort
Overall
64.7%
56.0%*
Quantizationsself-hosted
BF1656.0%FP854.8%AWQ-INT457.4%hardware →
Avg cost / sample$0.0011$0.0021
Avg speed / sample8.60s41.36s
By task
Object Detection (low)
61.0%
±1.2, Mean of 3 runs, range 59.9 to 62.2
$0.0015
38.1%
±5.7, Mean of 3 runs, range 33.5 to 44.9
$0
Object Detection (high)
62.3%
±1.2, Mean of 3 runs, range 61.4 to 63.8
$0.0050
–
Counting (low)
67.1%
±1.4, Mean of 3 runs, range 66.2 to 68.9
$0.0006
56.8%
±1.4, Mean of 3 runs, range 55.4 to 58.1
$0
Counting (high)
70.7%
±3.4, Mean of 3 runs, range 66.2 to 73.0
$0.0015
–
Identification (low)
83.3%
±1.6, Mean of 3 runs, range 81.3 to 84.4
$0.0004
83.3%
±1.6, Mean of 3 runs, range 81.3 to 84.4
$0
Identification (high)
84.4%
±6.3, Mean of 3 runs, range 78.1 to 90.6
$0.0007
–
OCR (low)
51.8%
$0.0011
–
by category
Single value
29.6%
Transcription
75.5%
Structured JSON
73.6%
Text localization
39.7%
OCR (high)
55.7%
$0.0041
–
by category
Single value
33.0%
Transcription
83.5%
Structured JSON
77.0%
Text localization
43.8%
Reasoning (low)
60.5%
±5.0, Mean of 3 runs, range 55.0 to 64.9
$0.0006
45.9%
±1.7, Mean of 3 runs, range 44.4 to 47.7
$0
Reasoning (high)
65.6%
±3.6, Mean of 3 runs, range 60.9 to 68.2
$0.0015
–

GPT-5.6 Luna vs Qwen3.5 9b: Overview

GPT-5.6 Luna

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. Luna supports 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.

Qwen3.5 9b

Qwen3.5-9B is a 9-billion-parameter multimodal foundation model developed by Alibaba Cloud's Qwen team, released on March 2, 2026 as part of the Qwen3.5 model family.

The model supports vision-language inputs through an early-fusion multimodal architecture built on a dense hybrid foundation of Gated Delta Networks and Gated Attention. It can also operate in a text-only mode by skipping the vision encoder during inference. It provides a 262,144-token context window (extensible to ~1M tokens via YaRN) and is released under the Apache License 2.0. Within the current AI landscape, Qwen3.5-9B offers a strong balance of capability and efficiency, making it well-suited for multimodal assistants, document analysis, long-context reasoning, and developer-deployed agentic systems.