Skip to content
LLMCompare
EvaluationsModels and pricesBlogPricing
中文
EvaluationsModels and pricesBlogPricing
中文

Last updated: 30 September 2026

Terms and Conditions

Please read these Terms and Conditions ("Terms") before using LLMCompare (the "Service"), operated by Funovate Technology LLC("we", "us" or "our"). By using the Service you agree to these Terms. If you do not agree with any part of them, do not use the Service.

1. Eligibility

You must be at least 18 years old to use the Service. By using the Service you state that you are at least 18 and that you can legally enter into these Terms.

2. Description of the Service

LLMCompare is a web tool for comparing AI models on test cases that you supply. It sends each test case to the models you select and records the output, the usage, the cost and the response time of every call. LLMCompare calls the models with its own accounts. You do not provide API keys.

LLMCompare is available only through its web pages. You may not use it as a programming interface to the models, and you may not resell access to the models through it.

We may change, suspend or discontinue the Service or any model in it at any time.

3. Accounts

You need an account to run evaluations. You sign in with a Google or Microsoft account. You are responsible for activity under your account. Tell us immediately at [email protected] if you believe someone else has used it.

4. Credits

4.1 How credits are charged

Running an evaluation costs credits. The charge is based on the model usage of each call in the run, including calls made by a judge model. Before a run starts, LLMCompare shows an estimated range of credits and holds the upper end of that range. When the run ends, the charge is settled against actual usage and the difference is returned.

  • A call that was not completed, for example because the provider limited the request rate or because of a fault on our side, costs no credits.
  • A call in which the model failed, for example a timeout, a refusal or an empty output, costs credits only when the provider charged for that call.

The "cost" shown in results and reports is the provider's published price in US dollars. It is shown to help you choose a model and is a different number from the credits you spend on LLMCompare.

4.2 Kinds of credits

  • Free daily credits expire at the end of the day on which you claim them.
  • Monthly credits come with a subscription and are reset at each billing period.
  • Purchased credits do not expire while your account is in good standing.

Credits cannot be transferred, sold or exchanged for money.

5. Payments

Payments are processed by Stripe. Prices are in US dollars. By giving payment details you authorise us to charge the applicable fees to that payment method and you state that you are allowed to use it. A subscription renews at the end of each billing period until you cancel it. Cancelling takes effect at the end of the period that you have paid for.

6. Refund policy

Credits that have been used are not refundable. Purchased credits that have not been used can be refunded when all of the following are true:

  • You ask within 14 days of the purchase.
  • No credits from that purchase have been used.
  • You send the request by email to [email protected].

Subscription fees are not refundable once the billing period has started.

7. Your content

You keep the rights you have in the test cases, prompts and files you submit. You give us permission to store and process them, and to send them to the model providers you select, for the purpose of running your evaluations.

Your evaluations are private. They are visible only to your account until you share or publish a report. When you share or publish a report, all of its test cases and outputs become visible to the people who can open it. Deleting an evaluation deletes its runs, outputs, uploaded files and published reports. See the Privacy Policy.

You are responsible for having the right to submit what you submit, including any personal data in it.

8. Model outputs

Outputs are generated by AI models operated by third parties. They can be wrong, incomplete or made up. Verify factual content before you rely on it. Evaluation results describe how the models behaved on your test cases at the time of the run, under the conditions recorded with the run. They are not a guarantee of how a model will behave later.

Subject to the terms of the model provider, we claim no ownership of the outputs of your runs. When you show an output publicly, say that it was generated by AI and name the model.

9. Acceptable use

You agree not to use the Service:

  • For any purpose that the provider of a model you select prohibits in its usage policies.
  • To generate content that is illegal, harmful, abusive or defamatory, or that infringes the rights of others.
  • To develop or train a model that competes with the models you evaluate, where the provider prohibits that.
  • To reverse engineer the Service, or to reach the models other than through the evaluation features of the web pages.
  • With automated tools in a way that exceeds reasonable use.
  • To pretend to be another person or organisation.

Model providers apply their own safety filters. A refusal by a model is recorded as that model's result. We may remove a published report and suspend or close an account that breaks these rules, without refund.

10. Names of providers and models

LLMCompare names providers and models in plain text to identify them. LLMCompare is not owned by, endorsed by or affiliated with any model provider. All names and trademarks belong to their owners.

11. Intellectual property

The Service, its original content and its features belong to Funovate Technology LLC and its licensors.

12. Privacy

The Privacy Policy is part of these Terms.

13. Disclaimer of warranties

THE SERVICE IS PROVIDED "AS IS" AND "AS AVAILABLE", WITHOUT WARRANTIES OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. WE DO NOT WARRANT THAT THE SERVICE WILL BE UNINTERRUPTED, ERROR-FREE OR COMPLETELY SECURE, OR THAT ANY MODEL WILL REMAIN AVAILABLE.

14. Limitation of liability

TO THE MAXIMUM EXTENT PERMITTED BY LAW, FUNOVATE TECHNOLOGY LLC IS NOT LIABLE FOR INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL OR PUNITIVE DAMAGES, INCLUDING LOSS OF PROFITS, DATA, USE OR GOODWILL, THAT RESULT FROM YOUR USE OF, OR INABILITY TO USE, THE SERVICE, OR FROM A DECISION MADE ON THE BASIS OF EVALUATION RESULTS.

OUR TOTAL LIABILITY TO YOU WILL NOT EXCEED THE GREATER OF (A) THE AMOUNT YOU PAID US IN THE 12 MONTHS BEFORE THE CLAIM, OR (B) USD 100.

15. Indemnification

You agree to defend and indemnify Funovate Technology LLC and its officers, directors, employees and agents against claims, damages, losses and costs, including reasonable legal fees, that arise from your breach of these Terms or from the content you submit.

16. Governing law and disputes

These Terms are governed by the laws of Japan, without regard to conflict-of-law rules. The Tokyo District Court, Japan, has exclusive jurisdiction over any dispute that arises from these Terms or the Service.

17. Changes to these Terms

We may change these Terms. When we do, we change the "Last updated" date at the top of this page. If you continue to use the Service after a change, you accept the new Terms.

18. Contact us

Email [email protected], or write to:

Funovate Technology LLC
2-19-7-704, Kanagawa, Kanagawa-ku, Yokohama-shi, Kanagawa, 221-0045, Japan
LLMCompare

Compare AI models on your own tasks. LLMCompare is not owned by a model provider.

Product

  • Evaluations
  • Models and prices
  • Pricing

Reading

  • Blog

Legal

  • Privacy
  • Terms
  • 中文