1stTop pick
Researched 6d agoQwen3.6-Plus
- MMMU
- 86%
- Output (from)
- $1.95 / 1M
Best Multimodal LLMs for Vision (2026)
Last refreshed 2026-05-18. Next refresh: weekly.
Top multimodal models that understand images, video, and documents, ranked by vision benchmarks, capabilities, pricing, and context window.
Top three picks
Opinionated short stack for this category — scroll for the full leaderboard, pricing, and compare links.
2ndShortlist
Researched 13d agoQwen3.5-397B-A17B
- MMMU
- 85%
- Output (from)
- $2.34 / 1M
3rdShortlist
Researched 8d agoGPT-5.4
- MMMU
- 82.1%
- Output (from)
- $15.00 / 1M
How we rank
Vision/multimodal leaders rank on MMMU (multimodal understanding), then recency.
- Eligibility — Models flagged `vision` or `multimodal` in seed data.
- Primary ranking — MMMU score, then newer release.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). When headline scores tie within ±0.5 pt (±10 Elo on Chatbot Arena), we pick the canonical SKU by lowest tracked input price, then GA over preview or limited access, then newest `release`. A folded sibling within the benchmark noise band can show a "Tied within margin" chip on that score cell.
- Pricing — Multimodal pricing often differs by modality — use provider rows for image/video-specific tiers.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Qwen3.6-Plus VisionTools MMMU: 86% | $0.33 | $1.95 | |
| 2 | Qwen3.5-397B-A17B ReasoningTools MMMU: 85% | $0.39 | $2.34 | |
| 3 | GPT-5.4 ReasoningTools MMMU: 82.1% | $2.50 | $15.00 | |
| 4 | Qwen3.6 Max Preview PreviewReasoningVisionTools MMMU: 82% | $1.04 | $6.24 | |
| 5 | Gemini 3 Pro VisionTools MMMU: 81% | $1.25 | $5.00 | |
| 6 | Claude Opus 4.5 ReasoningVisionTools MMMU: 80.7% | $5.00 | $25.00 | |
| 7 | Gemini 2.5 Flash VisionTools MMMU: 79.7% | $0.30 | $2.50 | |
| 8 | Claude Sonnet 4.5 ReasoningVisionTools MMMU: 77.8% | $3.00 | $15.00 | |
| 9 | Claude 3.7 Sonnet ReasoningVisionTools MMMU: 75% | $3.00 | $15.00 | |
| 10 | GPT-4o VisionTools MMMU: 69.1% | $2.50 | $10.00 | |
| 11 | Qwen2-VL-72B-Instruct Vision MMMU: 64.5% | $0.90 | $0.90 | |
| 12 | Llama 3.2 90B Vision Vision MMMU: 60.3% | $1.35 | $1.80 | |
| 13 | Llama 3.2 11B Vision Vision MMMU: 50.7% | $0.20 | $0.27 | |
| 14 | GLM-4V 9B MMMU: 48.3% | $0.05 | $0.25 | |
| 15 | Phi 3.5 Vision Instruct Vision MMMU: 43% | — | — | |
| 16 | Sora 2 MMMU: — | — | — | |
| 17 | Perceptron Mk1 ReasoningVision MMMU: — | $0.15 | $1.50 | |
| 18 | MiniCPM-V 4.6 Vision MMMU: — | — | — | |
| 19 | GPT Realtime 2 ReasoningTools MMMU: — | $32.00 | $64.00 | |
| 20 | GPT Realtime Translate MMMU: — | — | — |
Honorable mentions
Next seats in this ranking. Lines below are from each model's stored description in LLMReference seed data—spot-check the model page before relying on a capability claim.
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse MoE architecture, available for preview as part of the Qwen3.6 series.
82%
MMMU
Google DeepMind's most advanced reasoning Gemini model. Part of the Gemini 3 series with frontier-class intelligence, multimodal understanding, and 1M token context window.
81%
MMMU
Claude Opus 4.5 available on AWS Bedrock
80.7%
MMMU
Compare Top Picks
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest AI Agents & Agentic ModelsBest LLMs for ClassificationBest Open Source LLMsBest LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for Function Calling & Tool UseCheapest LLM APIs You Can Call Right NowBest Long Context LLMsBest Mainstream LLM APIs, RankedBest LLMs for EnterpriseBest Free LLMs You Can Use Right NowBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support