← Glossary Company
Artificial Analysis
An independent firm that benchmarks AI models on quality, speed and price.
Artificial Analysis measures AI models the way a consumer magazine tests cars: independent, standardised comparisons of quality, speed and cost. Its charts are widely cited when a new model claims to be the best or the cheapest.
When we quote their numbers, it is because vendor benchmarks flatter the vendor; independent measurement keeps everyone honest.
Mentioned in
-
Grok 4.6 Shows Up in GitHub Copilot, Two Days After Launch
-
Deepseek Gave Away Its Agent Software and Raised API Prices on the Same Day
-
Ling 3.0 Flash Is the Smartest Open Model of Its Size, and It Stopped Making Things Up
-
The Creator of Redis Made a Chinese Video Model Run on a Mac. Europeans Are Not Licensed to Use It
-
Nvidia's New Free Model Is Not the Smartest. It Is Just Very, Very Fast
-
Alibaba's newest model scores higher and guesses more: hallucination rate jumps from 23 to 40 percent
-
MiniMax released the weights for its H3 video model, and an open model now tops a video ranking for the first time
-
DeepSeek updated its cheap model and it now runs neck and neck with OpenAI's cheap model
-
Mira Murati's lab shrank its own model to a quarter of the size and lost one point
-
OpenAI's new transcription models are faster and 25 percent cheaper, but still not the most accurate
-
Kimi K3's weights are finally public, and they weigh 1.4 terabytes
-
Kimi K3: A Free-to-Download Model That Almost Keeps Up With the Big Names
-
Mira Murati's New Lab Ships Its First Model, and It's Built to Be Customized
-
Independent Numbers Are In: Meta's Muse Spark 1.1 Is a Serious Value Pick
-
GPT-5.6 Sol Nearly Matches the Best AI Model, at a Third of the Price
-
OpenAI Says a Third of a Popular AI Coding Test Is Broken
-
MiniMax M3: A Top-Tier AI Model You Can Download and Run Yourself