Draft:AI Stats Live
This draft's references do not show that the subject meets Wikipedia's criteria for inclusion for web content. The draft requires multiple published secondary sources that:
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|
A major contributor to this article appears to have a close connection with its subject. (October 2026) |
| Available in | English |
|---|---|
| Owner | Aistatslive |
| Commercial | No |
| Registration | Optional |
| Current status | Active |
AI Stats Live (also styled AIStatsLive) is a website that aggregates and publishes data on large language models and other artificial intelligence products, including benchmark results, API prices, context window sizes, and industry news.[1] The site states that it compiles its figures from third-party sources and links each value to its origin.[2]
History
[edit]AI Stats Live was launched in 2026 by Aistatslive.[3]
Content
[edit]Model leaderboards
[edit]The site ranks AI models on several separate measures rather than a single combined score.[4] Overall capability rankings use the Epoch Capabilities Index published by Epoch AI, while category leaderboards use individual benchmarks such as GPQA Diamond for reasoning and mock AIME problems for mathematics.[4] Additional rankings cover open-weight models, maximum context window, and price. Newly released models are listed separately until independent evaluation results are published; the site states that it does not use benchmark figures reported by model developers for its rankings.[1]
Pricing
[edit]The site lists API prices for models as reported by OpenRouter, expressed as a blended price per one million tokens (weighted 75% input, 25% output), and records price changes over time.[4]
AI product directory
[edit]A directory catalogues AI products, agents and companies by category, such as general assistants, coding tools, image and video generation, and inference providers. Products are ranked by popularity signals, which the site lists as including Wikipedia page views, Hacker News discussion, and software development kit downloads.[1]
News and events
[edit]The site aggregates AI-related news from press and primary sources, and generates event entries for model releases and API price or context-window changes.[1]
Everyday
[edit]A separate section, "Everyday", collects links to websites for general consumer tasks such as travel and price comparison.[1]
Data sources
[edit]According to the site, benchmark data is drawn from Epoch AI under a CC BY 4.0 licence and from Artificial Analysis; model listings and prices from OpenRouter; company information from Wikidata; page-view figures from the Wikimedia Foundation; and discussion data from Hacker News.[2] The site also offers an API.[5]
Reception
[edit]See also
[edit]References
[edit]External links
[edit]Category:Artificial intelligence websites Category:Internet properties established in 2026

Please delete the portions which were LLM-generated, and summarize in your own words a range of independent, reliable, published sources that discuss the subject. If you have used an LLM but you believe that your use is covered by one of the two exceptions (basic copyediting and translation between two languages in which you are fully fluent), please provide a transcript of the prompt(s) you used while writing your draft (see the how-to guide). Reviewers can make mistakes. If you have not received any LLM assistance, you may seek a second opinion at the AfC Help Desk.
See the advice page on large language models for more information.