JevBench · ImageJevBench · AudioJevBench

Submit a model for evaluation

Hand in a model and we will run it through our benchmarks and publish the result. Anyone can submit; no account needed.

How it works

The regular queue is free. Submissions are evaluated in the order we receive them.
Top-10 models are re-evaluated with every release; the rest of the leaderboard is re-evaluated less often.
Fast lane: results within 48 hours of payment, or a full automatic refund. It covers JevBench and ImageJevBench.

What we need

A name, how to reach the model (a GitHub link, a Hugging Face link or a public API URL, at least one), your email and the benchmarks you want. For an API model you can add a key; it is encrypted the moment we receive it and used only for this evaluation. Never paste keys anywhere else.

Your submission

Model nameGitHub linkHugging Face linkAPI URL

Add at least one of the three. An API URL must be a public https address.

API key (optional)Stored encrypted, never shown again, used only for this evaluation and deleted afterwards. Add an API URL to enable this field.Description / notes (optional)Contact emailX handle (optional)

Benchmarks

Choose at least one.

JevBenchText-based Jev-class decisionsImageJevBenchImage-based decision tasksAudioJevBenchAudio-based decision tasks

Follow-up of a model already on the leaderboard?

Fast lane: results within 48 hours of payment, or a full automatic refund

We use your email only to confirm and to report back on this submission. Privacy.

We store what you enter here to run and report on the evaluation, and delete a submitted API key afterwards. See the privacy policy and terms.