Compare the best 97 visual question answering models and try 86 of them on your own images, free in the Roboflow Playground. 37 are open-weight, so you can self-host them for free under their licenses.
97 models · 37 open-weight · 86 free to try · prices synced Nov 8, 2026
Gemini 4 Argon scores 89.4% on Roboflow's Vision Evals visual reasoning benchmark (low effort, 65 models, mean of 3 runs), ahead of GPT-6 Astra at 87.2%. Updated Oct 26, 2026. See the full ranking.
Benchmark Leader
Gemini 4 Argon
Highest score on Roboflow's Vision Evals visual reasoning benchmark, 65 vision language models tested
Open-Weight Leader
Muse Spark Open
Best score among the open-weight models, #27 of 65 overall on Roboflow's Vision Evals visual reasoning benchmark
Fastest on Benchmark
GPT-6.1 Terra
Quickest within 15 points of the leader in Roboflow's Vision Evals visual reasoning benchmark runs: 2.5s per request on average, scoring 85.4%
Lowest Measured Cost
GPT-6.1 Terra
Cheapest within 15 points of the leader in Roboflow's Vision Evals visual reasoning benchmark runs: $0.0016 per request as measured, not list price, scoring 85.4%
37 models with downloadable weights you can self-host under their licenses (Custom, MIT, and Apache 2.0). 28 run live in the Playground through hosted APIs, so self-hosting is optional.
| Actions | ||||
|---|---|---|---|---|
Muse Spark OpenMeta | 816B total / 42B active | Custom | Oct 2026 | |
Mistral Large 4Mistral | 1.05T total, 49B active | Custom | Oct 2026 | |
MiMo V2.6 FlashXiaomi | 309B total, 15B active | MIT | Sep 2026 | |
MiMo V2.6 ProXiaomi | 1.02T total, 42B active | MIT | Sep 2026 | |
GLM 5.3 FlashZ.ai | 320B total, 18B active | MIT | Aug 2026 | |
Qwen3.8 27BQwen | 27.78B | Apache 2.0 | Aug 2026 | |
Muse Glimmer 30BMeta | 29.6B | Apache 2.0 | Aug 2026 | |
Kimi K3Moonshot AI | 2.8T | Modified MIT | Jul 2026 | |
Gemma 4 12BGoogle | 12B | Apache 2.0 | Jun 2026 | |
Qwen3.6 27BQwen | 27B | Apache 2.0 | Apr 2026 | |
Qwen3.6 35B A3BQwen | 35B total, 3B active | Apache 2.0 | Apr 2026 | |
Gemma 4 26B A4BGoogle | 25.2B | Apache 2.0 | Apr 2026 | |
Gemma 4 31BGoogle | 31B | Apache 2.0 | Apr 2026 | |
GLM-OCRZ.ai | 0.9B | MIT | Mar 2026 | |
Qwen3.5 9bQwen | 9B | Apache 2.0 | Mar 2026 | |
| 122B | Apache 2.0 | Feb 2026 | ||
Qwen3.5 35B A3BQwen | 35B | Apache 2.0 | Feb 2026 | |
Qwen3.5-27BQwen | 27B | Apache 2.0 | Feb 2026 | |
| 397B | Apache 2.0 | Feb 2026 | ||
Kimi K2.5Moonshot AI | 1T | Modified MIT | Jan 2026 | |
| 8.8B | Apache 2.0 | Oct 2025 | ||
| 31B | Apache 2.0 | Oct 2025 | ||
| 235B | Apache 2.0 | Sep 2025 | ||
Llama 4 MaverickMeta | 400B | Custom | Apr 2025 | |
Llama 4 ScoutMeta | 109B | Custom | Apr 2025 | |
Mistral Small 3.1 24BMistral | 24B | Apache 2.0 | Mar 2025 | |
Gemma 3 12BGoogle | 12B | Custom | Mar 2025 | |
Gemma 3 27BGoogle | — | Custom | Mar 2025 | |
Gemma 3 4BGoogle | 4B | Custom | Mar 2025 | |
SmolVLM2Hugging Face | 256M – 2.2B | Apache 2.0 | Feb 2025 | |
| 7B | Apache 2.0 | Jan 2025 | ||
PaliGemma 2Google | 3B, 10B, 28B | Custom | Dec 2024 | |
Pixtral 12BMistral | 12B | Apache 2.0 | Sep 2024 | |
PaliGemmaGoogle | 3B | Custom | May 2024 | |
Moondream 2Moondream | ~2B | Apache 2.0 | Jan 2024 | |
LLaVA-1.5Microsoft | 7B, 13B | Custom | Oct 2023 | |
Qwen-VLQwen | — | Custom | Aug 2023 |
60 proprietary models where the weights aren't downloadable: access is through each provider's API and billed by them. Try 58 of them free in the Playground.
| Actions | |||||
|---|---|---|---|---|---|
GPT-6.1 TerraOpenAI NEW | $1.00 | $5.00 | 1.1M | Oct 2026 | |
Gemini 4 ArgonGoogle | $2.00 | $10.00 | 1M | Oct 2026 | |
Muse WonderMeta | $4.00 | $20.00 | 1.0M | Oct 2026 | |
Claude Haiku 5.5Anthropic | $0.10 | $0.50 | 1M | Oct 2026 | |
GPT-6.1 SolOpenAI | $2.00 | $10.00 | 1.1M | Sep 2026 | |
Claude Sonnet 5.5Anthropic | $2.00 | $10.00 | 1M | Sep 2026 | |
Claude Opus 5.5Anthropic | $4.00 | $20.00 | 1M | Sep 2026 | |
GPT-6 LunaOpenAI | $0.10 | $0.50 | 1.1M | Sep 2026 | |
GPT-6 SolOpenAI | $2.00 | $10.00 | 1.1M | Sep 2026 | |
Grok 4.7SpaceXAI | $2.00 | $6.00 | 500K | Sep 2026 | |
GPT-6 AstraOpenAI | $10.00 | $50.00 | 1.1M | Sep 2026 | |
Gemini 3.8 FlashGoogle | $0.83 | $4.13 | 1.0M | Sep 2026 | |
Muse Spark 1.3Meta | $1.25 | $4.25 | 1.0M | Sep 2026 | |
Claude Fable 5.1Anthropic | $10.00 | $50.00 | 1M | Sep 2026 | |
Qwen3.8 FlashQwen | $0.15 | $0.47 | 1M | Aug 2026 | |
Gemini 3.7 FlashGoogle | $0.75 | $3.75 | 1.0M | Aug 2026 | |
Grok 4.6SpaceXAI | $2.00 | $6.00 | 500K | Aug 2026 | |
Muse Spark 1.2Meta | $1.25 | $4.25 | 1.0M | Aug 2026 | |
Qwen3.8 MaxQwen | — | — | 984K | Aug 2026 | |
Qwen3.7 FlashQwen | $0.030 | $0.13 | 1M | Jul 2026 | |
Claude Opus 5Anthropic | $5.00 | $25.00 | 1M | Jul 2026 | |
Gemini 3.5 Flash-LiteGoogle | $0.30 | $2.50 | 1.0M | Jul 2026 | |
Gemini 3.6 FlashGoogle | $0.75 | $3.75 | 1M | Jul 2026 | |
GPT-5.6 LunaOpenAI | $0.20 | $1.20 | 1.5M | Jul 2026 | |
GPT-5.6 SolOpenAI | $4.00 | $20.00 | 1.5M | Jul 2026 | |
GPT-5.6 TerraOpenAI | $2.00 | $12.00 | 1.1M | Jul 2026 | |
Muse Spark 1.1Meta | $1.25 | $4.25 | 1.0M | Jul 2026 | |
Grok 4.5SpaceXAI | $2.00 | $6.00 | 500K | Jul 2026 | |
Claude Sonnet 5Anthropic | $2.00 | $10.00 | 1M | Jun 2026 | |
Claude Fable 5Anthropic | $10.00 | $50.00 | 1M | Jun 2026 | |
Qwen3.7 PlusQwen | $0.32 | $1.28 | — | Jun 2026 | |
Claude Opus 4.8Anthropic | $5.00 | $25.00 | 1M | May 2026 | |
Gemini 3.5 FlashGoogle | $1.50 | $9.00 | 1.0M | May 2026 | |
GPT-5.5OpenAI | $5.00 | $30.00 | 1M | Apr 2026 | |
Claude Opus 4.7Anthropic | $5.00 | $25.00 | 1M | Apr 2026 | |
Qwen3.6 FlashQwen | $0.19 | $1.13 | 1M | Apr 2026 | |
Qwen3.6 PlusQwen | $0.33 | $1.95 | 1M | Apr 2026 | |
GLM 5V TurboZ.ai | $1.20 | $4.00 | 200K | Apr 2026 | |
GPT-5.4 MiniOpenAI | $0.75 | $4.50 | 400K | Mar 2026 | |
GPT-5.4 NanoOpenAI | $0.20 | $1.25 | 400K | Mar 2026 | |
GPT-5.4OpenAI | $2.50 | $15.00 | 1.1M | Mar 2026 | |
Gemini 3.1 Flash-LiteGoogle | $0.25 | $1.50 | 1M | Mar 2026 | |
Gemini 3.1 ProGoogle | $2.00 | $12.00 | 1M | Feb 2026 | |
Claude Sonnet 4.6Anthropic | $3.00 | $15.00 | 1M | Feb 2026 | |
Claude Opus 4.6 Anthropic | $5.00 | $25.00 | 1M | Feb 2026 | |
Gemini 3 FlashGoogle | $0.50 | $3.00 | 1M | Dec 2025 | |
GPT-5.2OpenAI | $1.75 | $14.00 | 400K | Dec 2025 | |
Claude Opus 4.5Anthropic | $5.00 | $25.00 | 200K | Nov 2025 | |
GPT-5.1OpenAI | $1.25 | $10.00 | 196K | Nov 2025 | |
Claude Haiku 4.5Anthropic | $1.00 | $5.00 | 200K | Oct 2025 | |
Claude Sonnet 4.5Anthropic | $3.00 | $15.00 | 200K | Sep 2025 | |
Mistral Medium 3.1Mistral | $0.40 | $2.00 | 128K | Aug 2025 | |
GPT-5OpenAI | $1.25 | $10.00 | — | Aug 2025 | |
GPT-5 MiniOpenAI | $0.25 | $2.00 | 400K | Aug 2025 | |
GPT-5 NanoOpenAI | $0.050 | $0.40 | 400K | Aug 2025 | |
Gemini 2.5 Flash-LiteGoogle | $0.10 | $0.40 | 1M | Jul 2025 | |
Gemini 2.5 FlashGoogle | $0.30 | $2.50 | 1M | Jul 2025 | |
Grok 4SpaceXAI | — | — | — | Jul 2025 | |
Gemini 2.5 ProGoogle | $1.25 | $10.00 | 1M | Jun 2025 | |
Qwen VL MaxQwen | — | — | — | Feb 2025 |
VQA quality tracks general reasoning ability more than any other vision task: the model must read the question, find the evidence in the image, and reason to an answer. That makes the choice mostly about how hard your questions are and how expensive a wrong answer is.
Questions that chain steps (counting plus comparison, reading text then interpreting it, spatial reasoning in cluttered scenes) separate the top models from the rest quickly. If your questions are open-ended or your users type anything they want, the frontier tier is the safe default; the visual reasoning benchmark in Roboflow's Vision Evals shows how the current models actually rank on this.
When the question is fixed and simple ("is the shelf empty?", "is a person present?"), a small open VLM answers at a fraction of the cost, and often a trained classifier or detector answers it even more reliably: a fixed question is really a classification or detection task in disguise, and converting it usually improves both accuracy and unit economics.
VQA models answer fluently whether or not they are right. For production use, prefer questions whose answers can be checked (counts you can verify with a detector, text you can verify with OCR), ask for the evidence in the answer, and treat free-form answers about safety-critical content as drafts for review rather than decisions.
The bottom line: Open-ended questions need a frontier model; a fixed, repeated question is usually a classification or detection task wearing a question mark, and converting it is cheaper and more reliable.
On Roboflow's Vision Evals visual reasoning benchmark (65 models tested, updated Oct 26, 2026), Gemini 4 Argon by Google currently scores highest at 89.4%. The full ranking is on our evals page. For fixed categories in production, a model fine-tuned on your own data still often wins.
Yes. 37 of the 97 visual question answering models here are open-weight (for example Muse Spark Open, Qwen3.8 27B, and Qwen3.6 27B), free to self-host under their licenses (Custom, MIT, and Apache 2.0).
Yes. You can run 86 of them in the Roboflow Playground for free. Upload an image and compare the models' output side by side, no setup required.
Explore other vision task pages, compare models head to head, or browse the full model catalog.