Skip to content
Jev Tracker
BenchmarksExperimentsAccessLimitationsLatest
Explore Jev Tracker
BenchmarksExperimentsAccessLimitationsLatest
Home/About

About Jev Tracker

How we check claims.

Understand the sources, checks and limits behind Jev Tracker coverage before relying on a conclusion.

Our method Corrections
Concept illustration of a lens examining a graphite and green cube.
Concept illustration, not a test result.

Independent coverage. A defined scope.

Jev Tracker is an independent publication for people following Jev. We explain published experiments, access options, performance claims and capability limits in plain language.

We are not TypeSafe AI and have no affiliation, partnership or endorsement from the model provider. This site is not a Jev chat service, account portal or developer tool.

This publication uses the public name Jev Tracker. Contact and correction enquiries are handled through the email address listed on our Contact page.

Evidence before conclusions.

A provider’s announcement, an integration guide and a user’s report answer different questions. We keep those distinctions visible.

Who said it matters

A source label identifies the publisher’s relationship to a claim. It does not certify the result, establish funding independence or rank accuracy.

Official

Material from the model provider, including announcements and documentation.

Useful for what the provider states. Not an independent measurement.

Integration

A platform or framework documenting how it connects to Jev.

Describes that integration. It does not prove every account can use it.

Independent

Analysis published outside the model provider.

Check the author’s methods, incentives and evidence. Outside authorship alone is not reproducibility.

Self-reported

An author’s account of their own experience or result.

Conditions may be incomplete. We do not present it as a result reproduced by Jev Tracker.

Community

Discussion, synthesis or aggregated reports from a wider group.

Selection, missing context and incompatible tasks can make comparisons misleading.

Checked is not reproduced

Current coverage is document-based. Jev Tracker has not independently run the featured experiments or successfully called Jev to verify access.

  1. Inspect the original material

    Read the source behind the claim, identify who published it and record the source URL. Prefer original documentation over repeated summaries.

  2. Keep the conditions attached

    Record the relevant task, model or integration, comparison baseline and limitations. A peak result stays a peak, not a typical outcome.

  3. Separate evidence from interpretation

    Explain what the source establishes and what remains unknown. Missing documentation does not by itself prove a feature is impossible.

  4. Publish a dated record

    We review and update our coverage manually. Each source-check date records when we last reviewed the cited material.

Three different evidence thresholds

Source inspected
The cited material was reviewed. This is what our source-check timestamps describe.
Access tested
Would require a successful request under stated account and model conditions. Reading availability documentation is not this test.
Result reproduced
Would require a documented run with inputs, setup and results. A linked demonstration is not a Jev Tracker reproduction.

Read the date, not just the claim

Published
When the source was published, if known. We do not substitute our check date for a missing publication date.
Event date
When the reported event happened. A later review of the source does not turn an old event into new news.
Source checked
When we inspected the cited material, shown with a UTC time. It is not a certificate of model performance or current account access.
Stale, partial or unavailable information

Access entries become Stale after more than 72 hours without a new source check. Other pages retain their item-level dates and model scope; they are not live monitoring feeds.

Unknown requirements or prices remain Not yet verified. Partial evidence stays qualified. A known unavailable source is labelled instead of silently replaced with unsupported certainty.

Keep changes in the open

For material corrections, we record the affected claim, previous wording, new evidence, reason for the change and date. We distinguish updates to our coverage from changes to the product.

The limitations guide records how explicit model documentation resolved our earlier uncertainty about image input. The note preserves what changed in our coverage.

Read a coverage update

Send a correction

Corrections can be sent by email using our Corrections page. Include the affected page, claim and supporting source. We do not promise a response time or automatic publication.

Correction guidance

Illustrations are not evidence

Concept illustrations explain themes. They are not product screenshots, experiment outputs or evidence that Jev Tracker ran a test.

Put the method to work.

Examine performance claims Explore sourced experiments
Jev Tracker

Independent coverage of Jev. No affiliation, partnership or endorsement by TypeSafe AI.

Evidence before conclusions.

Sources checked. Uncertainty stated. A source label is not a seal of approval.

About and editorial method

Keep the record clear.

We explain what changed and why.

Corrections and updates
ContactPrivacy

Jev Tracker. Editorial illustrations are concepts, not product screenshots.