Claims are easy. Reality is the hard part.
Every AI lab publishes benchmark numbers when it ships a model. Most of those numbers are accurate. Few of them tell you what the model is actually like to use. trackai tracks both, side by side, and treats them differently — because they come from different places and deserve different levels of trust.
Two layers of data
CLAIM — WHAT THE PROVIDER SAYS
For each model we record what the lab itself announced: a short summary of what shipped, whichever benchmark figures that lab chose to publish, and a link straight to its announcement. Nothing here is independently verified — it is the provider’s own account of its own product, presented as exactly that.
Two things worth knowing when you read these numbers. Labs quote the benchmarks that flatter them, so the figures on one model page are rarely directly comparable to another’s. And where a summary was drafted automatically from the announcement, the page says so and links the source, so you can check it in one click.
REALITY — REAL-WORLD TESTS
A report is a real test: someone putting a model to work on an actual task and showing what came out. Most come from X, where people share what they’ve built with a new model. Those posts are hand-picked — each one is read and saved to a dedicated bookmark folder, which trackai imports automatically — and they appear exactly as posted, with the author’s own attribution and a link back.
The rest are shared by readers through this site: a one-line takeaway, a task tag and a link to the source. Nothing here is confirmed information the way a release date is; each report is one person’s account, and it’s presented that way.
How reports are chosen
Every report on trackai has been picked by a person. Posts from X are chosen at the source: one is only imported after it’s been read and bookmarked as a genuine test, so choosing it is the review. Reports shared by readers wait in a review queue until they’re approved, and rejected ones never appear.
Posts that only talk about a model — opinions, hype, launch-day reactions — are left out; a report has to show the model being used. There’s no algorithmic ranking or voting behind what’s published.
Reading the status marker
The dot next to a model’s name on the timeline shows how confirmed it is:
- Rumored — talked about, nothing official yet. Sourced from public tech coverage, not the provider, and re-checked daily — a predicted date or summary can change, or the model can simply vanish if the chatter dies down. Replaced entirely the moment a real announcement is found.
- Announced — the provider has confirmed it’s coming.
- Released — shipped, with benchmark data attached.
Submit a report
If you’ve tried a model on a real task and it’s not reflected here yet, submit a report. One line on what happened, a link to back it up, and the task category it falls under.
Who’s behind this
trackai is a concept by Augustine Osei, built by August Engine, and documented in public on The August Dispatch — a blog documenting the decisions, dead ends, and rewrites behind it as they happen, not a polished writeup after the fact.