AI Models Pass Vision Tests Without Seeing the Images
A Stanford study shows frontier AI models achieve 70-80% of visual benchmark scores with no images provided, exposing a fundamental flaw in how multimodal AI is evaluated.
Articles Tagged "Multimodal"
Qwen3.5-Omni Does 10-Hour Audio and 4M Video Frames
Alibaba's Qwen3.5-Omni handles audio, video, images, and text in a single model pass - and generates speech in real time. The Plus variant hits SOTA on 215 benchmarks and edges out Gemini 3.1 Pro on audio tasks.
Muse Spark Review: Strong on Health, Weak on Code
Meta's first proprietary frontier model leads on HealthBench Hard and scientific reasoning but trails rivals in coding and agentic tasks - with no public API yet.
EXAONE 4.5: LG's Open VLM Beats GPT-5-mini on STEM
LG AI Research released EXAONE 4.5, a 33B open-weight vision-language model that posts higher STEM scores than GPT-5-mini and Claude 4.5 Sonnet - but a non-commercial license caps its real-world reach.
Muse Spark
Meta's first closed-source frontier model scores 52 on the Artificial Analysis Intelligence Index, leads on HealthBench Hard, and ships free at meta.ai - but has no public API yet.
Meta Muse Spark Launches, Ranks 4th Among Frontier Models
Meta Superintelligence Labs releases Muse Spark, its first AI model built from scratch in nine months, landing 4th on the Artificial Analysis Intelligence Index.
Google Gemma 4
Gemma 4 is Google DeepMind's most capable open model family: four variants from 2B to 31B, Apache 2.0 license, multimodal across text/image/video/audio, and the 31B Dense ranking #3 on Chatbot Arena against all open-weight models globally.
Gemma 4 Review: Google's Biggest Open-Source Bet
Google's Gemma 4 family - four models, full Apache 2.0 licensing, and benchmark scores that challenge models 10x their size - is the most consequential open-weight release of 2026 so far.
Google Gemma 4 Ships Four Open Models Under Apache 2.0
Google releases Gemma 4 with a 26B MoE, 31B Dense, and two edge variants under Apache 2.0 - claiming the highest intelligence-per-parameter of any open model.
AI Vision Input Limits - What Every Provider Hides
A technical comparison of how Claude, GPT-4o, Gemini, Grok, Pixtral, Qwen, and DeepSeek handle image inputs - resizing pipelines, token math, and undocumented gotchas.
Multimodal AI Explained - A Beginner's Guide
Multimodal AI can see, hear, and read at once - here's how it works and why it matters for everyday users.
Kimi K2.5 Review: Open Weights, Agent Swarms, Caveats
Moonshot AI's Kimi K2.5 delivers best-in-class open-weight math and a genuinely novel multi-agent architecture, but a brutal hallucination rate and slow inference limit its real-world reliability.
