JevBench · priority evaluation requests
Request a priority evaluation
JevBench is independent, volunteer-run and open source. We do this in our spare time, and GPU and token costs have become a real problem. A priority request helps cover those costs and moves a model earlier in our evaluation queue.
New: submit any model (free regular queue or fast lane) at /submit.
The regular benchmark remains free. We continue to re-score models on our own schedule, including weekly batches, at no cost.
Fees
Per benchmark for API-served models or open models up to about 9B parameters.
Per benchmark for larger open models that we run on our GPUs.
Choosing both JevBench and ImageJevBench charges the selected tier twice. Applicable tax is calculated at checkout.
What the fee does and does not change
- Payment buys earlier scheduling only. It never buys a different method, score or rank. Every model uses the same frozen task set and rules.
- We decide which models we evaluate and when. We may also evaluate any model early on our own if it is of public interest.
- Every submission goes through code review. We refuse and fully refund requests that are unsafe or cannot be evaluated fairly.
- We provide results within 48 hours of payment. If we miss that deadline, the payment is automatically refunded in full. The clock pauses while we wait for information requested from you.
- A public paid run carries a visible “priority run” marker in the data. A private report is never published without your team's consent. We may still evaluate the model later on our own schedule if it becomes a matter of public interest.
Request a run
Think you should be exempt from this fee?
For example, if you work for a non-profit or in research, contact us and briefly explain your request. We can waive the fee at our discretion.
Operated by productivity-boost.com Betriebs UG (haftungsbeschränkt) & Co. KG · Imprint · Terms · Privacy