Roboflow

GPT-5.6 Luna vs Qwen3.6 35B A3B

Qwen3.6 35B A3B averages 64.8% across four Vision Evals tasks and GPT-5.6 Luna 64.7% across five (#38 and #39 of 73 models), so they are effectively tied.

  • GPT-5.6 Luna wins all 4 tasks both ran, with its widest lead on reasoning (60.5% vs 54.8%).
  • GPT-5.6 Luna is cheaper: $0.0011 vs $0.0012 overall average cost per sample.
  • GPT-5.6 Luna is faster: 8.6s vs 27.1s per sample.

Compare GPT-5.6 Luna vs Qwen3.6 35B A3B 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 Luna
Run to compare this model.
QwenQwen3.6 35B A3B
Run to compare this model.

GPT-5.6 Luna vs Qwen3.6 35B A3B on Vision Evals

Score by taskGPT-5.6 LunaQwen3.6 35B A3B
Reasoning
60.5
54.8
Object Detection
61.0
57.0
Counting
67.1
65.3
Identification
83.3
82.3

Roboflow Vision Evals. Full breakdown below.

GPT-5.6 Luna vs Qwen3.6 35B A3B Comparison Table

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

PropertyGPT-5.6 LunaQwen3.6 35B A3B
OrganizationOpenAIQwen
Categoryclosedopen
Modalitymultimodalmultimodal
Release DateJul 2026Apr 2026
Context Window1.5M262K
ParametersUnknown35B total, 3B active
LicenseProprietaryApache 2.0
Commercial usecommercial use per vendor termsfree for commercial use
Pricing per 1M tokens
Input $/1M$0.200$0.100
Output $/1M$1.20$0.900
Vision Tasks
Phrase GroundingNot listedSupported
Video ClassificationNot 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
64.7%
64.8%*
Quantizationsself-hosted
FP864.8%AWQ-INT460.9%hardware →
Avg cost / sample$0.0011$0.0012
Avg speed / sample8.60s27.10s
By task
Object Detection (low)
61.0%
±1.2, Mean of 3 runs, range 59.9 to 62.2
$0.0015
57.0%
±1.3, Mean of 3 runs, range 56.1 to 58.7
$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
65.3%
±2.7, Mean of 3 runs, range 62.2 to 67.6
$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
82.3%
±6.3, Mean of 3 runs, range 75.0 to 87.5
$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
54.8%
±1.3, Mean of 3 runs, range 53.0 to 55.6
$0
Reasoning (high)
65.6%
±3.6, Mean of 3 runs, range 60.9 to 68.2
$0.0015
–

GPT-5.6 Luna vs Qwen3.6 35B A3B: 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.

Qwen3.6 35B A3B

Qwen3.6-35B-A3B is a sparse Mixture-of-Experts (MoE) multimodal language model developed by the Qwen team at Alibaba Group. It carries 35 billion total parameters but activates only approximately 3 billion per forward pass via a learned routing mechanism, giving it the representational capacity of a large dense model at a fraction of the inference compute. The model is natively multimodal, processing images, documents, and video alongside text as a core architectural capability rather than an add-on. It supports a native context window of 262,144 tokens, extensible up to 1,010,000 tokens via YaRN. A key design feature is the unified thinking/non-thinking mode framework: users can switch between deliberate chain-of-thought reasoning and fast direct responses within a single model, and a "thinking preservation" option retains reasoning context across multi-turn agentic workflows to reduce redundant computation.

The model is specifically optimized for agentic coding tasks, including repository-level reasoning, frontend workflow generation, multi-step tool use, and MCP (Model Context Protocol) integration. For vision-language tasks it achieves 92.0 on RefCOCO, 89.9 on OmniDocBench 1.5, and 83.7 on VideoMMMU. The model also supports Multi-Token Prediction (MTP) for speculative decoding. All Qwen3.6 open-weight models are released under the Apache 2.0 license.