BenchmarkFree
Start Eval

Legal

Terms of Service

Effective date: 6 July 2026 · English version is authoritative.

1. Agreement

These Terms of Service (“Terms”) govern your access to and use of BenchmarkFree, operated at https://benchmarkfree.dev by benchmarkfree.dev (“we”, “us”, or “our”).

By accessing or using the Service, you agree to these Terms and our Privacy Policy. If you do not agree, do not use the Service.

The English version of these Terms is the authoritative version.

2. The Service

BenchmarkFree provides tools for evaluating large language models (LLMs) in real-world scenarios, including quick comparisons, batch tasks, prompt libraries, model configuration, automated judge scoring, user score feedback, and public leaderboards.

We may modify, suspend, or discontinue any part of the Service at any time, with or without notice, to maintain security, comply with law, or improve the product.

3. Eligibility

You must be at least 16 years old to use the Service, or older if a higher age is required by the laws of your country or region.

You represent that you have the legal capacity to enter into these Terms and that your use complies with all applicable laws.

If we become aware that a user is below the applicable minimum age, we will promptly suspend the account and delete associated personal data, except where a longer retention period is required by law.

4. Accounts

  • You are responsible for maintaining the confidentiality of your account credentials.
  • You are responsible for all activity under your account.
  • You must provide accurate registration information and keep it up to date.
  • Notify us promptly at [email protected] if you suspect unauthorised access.

We may suspend or terminate accounts that violate these Terms or pose security or legal risk.

5. Acceptable use

You agree not to:

  • Use the Service for unlawful, harmful, fraudulent, or abusive purposes
  • Upload, submit, store, transmit, or otherwise make available through the Service any User Content that is illegal under applicable law, including content that:
    • Is obscene, pornographic, or sexually exploitative of minors (child sexual abuse material)
    • Depicts, promotes, or incites violence, terrorism, or serious physical harm against persons or groups
    • Constitutes hate speech, harassment, or credible threats against individuals or protected groups
    • Promotes illegal drugs, weapons trafficking, fraud, or other serious criminal activity
    • Violates export control, sanctions, or other national-security-related restrictions
  • Submit content that infringes intellectual property, privacy, or other rights of third parties
  • Upload malware, attempt unauthorised access, or interfere with the Service or its infrastructure
  • Scrape, reverse engineer, or overload the Service except as expressly permitted
  • Misrepresent evaluation results or manipulate leaderboards through deceptive means
  • Use the Service to process special categories of personal data as defined under applicable data protection law, including health, biometric, genetic, or children's data

We may remove or restrict access to User Content, suspend or terminate accounts, and cooperate with law enforcement or other competent authorities where we reasonably believe content or conduct violates these Terms or applicable law. We are not obligated to monitor all User Content but reserve the right to do so for safety, legal compliance, and integrity of the Service.

6. Your content and prompts

You retain ownership of prompts, configurations, and other content you submit (“User Content”), subject to the licence below.

You grant us a worldwide, non-exclusive licence to host, process, transmit, display, and analyse User Content solely to provide and improve the Service, including sending content to model providers you select for inference or judging.

The licence does not include the right to use User Content to train, fine-tune, or develop AI models. We do not use your prompts or evaluation outputs to train our own or third-party foundation models.

You represent that you have all rights necessary to submit User Content, that your User Content complies with Section 5 (Acceptable use), and that doing so does not violate any law or third-party rights.

7. Public leaderboards and visibility

Certain evaluation results may contribute to public leaderboards when eligibility criteria are met (for example, use of publicly available prompts, completed scoring, and minimum participation thresholds). Leaderboard entries typically show model identifiers and aggregated scores, not your account name or email address.

Your personal account details are not published on public leaderboards. Prompt text and raw model outputs from your sessions are not displayed publicly by default.

You can avoid contributing to public leaderboards by using private prompts, keeping batch tasks non-public, or not completing flows that qualify for public ranking. If you believe data has been included in error, contact [email protected].

Further details on how leaderboard data is derived may be published in product documentation or algorithm descriptions on the Service.

8. Third-party models and API keys

The Service may invoke third-party AI providers (e.g. OpenAI, Anthropic, Google, Azure, or other endpoints you configure). Your use of those providers is subject to their separate terms and pricing. You are responsible for any fees they charge and for compliance with their policies.

If you provide API keys or credentials, you authorise us to use them solely to make API calls to the model providers you select, on your behalf and at your direction, to run evaluations you explicitly initiate (including connection validation). This means your keys may be used to send requests to those third-party providers, not only stored on our servers.

Keys are encrypted at rest and transmitted over encrypted connections. They are not shared with other users. You remain responsible for securing, rotating, and permissioning your keys outside the Service.

9. Evaluation results and disclaimers

Automated judge scores, rankings, latency metrics, and other outputs are provided for informational and comparative purposes only. They do not constitute professional, legal, financial, or technical advice.

LLM outputs may be inaccurate, incomplete, biased, or unsafe. You are solely responsible for reviewing outputs before relying on them in production or high-risk contexts.

We do not guarantee uninterrupted, error-free, or fit-for-purpose operation of the Service or any model integration.

We are not responsible for any failure, interruption, or degradation of third-party model provider services, including API unavailability, rate limiting, authentication errors, model deprecation, or changes to provider terms or pricing.

10. Intellectual property

The Service, including its software, design, branding, documentation, and original content (excluding User Content), is owned by us or our licensors and protected by applicable intellectual property laws.

You may not copy, modify, distribute, or create derivative works of the Service except as permitted by law or with our written consent.

11. Privacy

Our collection and use of personal data is described in the Privacy Policy. By using the Service, you acknowledge that policy.

12. Termination and data deletion

You may stop using the Service at any time. To request deletion of your account and associated personal data, email [email protected] from the address linked to your account with “Account deletion request” in the subject line.

We will acknowledge verified deletion requests within a reasonable time and aim to complete deletion within 30 days, unless a longer period is permitted by law. Some data may be retained where required for legal compliance, dispute resolution, security, or enforcement of these Terms (for example, audit logs or records we are legally obliged to keep). Retained data will be limited to what is necessary and protected appropriately.

We may terminate or suspend access immediately if you breach these Terms or if required for security or legal reasons. Provisions that by nature should survive termination (including disclaimers, limitations of liability, and governing law) will survive.

13. Disclaimer of warranties

THE SERVICE IS PROVIDED “AS IS” AND “AS AVAILABLE” WITHOUT WARRANTIES OF ANY KIND, WHETHER EXPRESS, IMPLIED, OR STATUTORY, INCLUDING IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, AND NON-INFRINGEMENT, TO THE FULLEST EXTENT PERMITTED BY LAW.

To the fullest extent permitted by law, we provide the Service without warranties of any kind, whether express or implied, including that the Service will be uninterrupted, error-free, secure, or fit for your particular purpose.

14. Limitation of liability

TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, WE AND OUR AFFILIATES, OFFICERS, DIRECTORS, EMPLOYEES, AND AGENTS WILL NOT BE LIABLE FOR ANY INDIRECT, INCIDENTAL, SPECIAL, CONSEQUENTIAL, OR PUNITIVE DAMAGES, OR ANY LOSS OF PROFITS, DATA, GOODWILL, OR BUSINESS OPPORTUNITIES, ARISING FROM OR RELATED TO YOUR USE OF THE SERVICE.

OUR TOTAL LIABILITY FOR ANY CLAIM ARISING OUT OF OR RELATING TO THE SERVICE OR THESE TERMS WILL NOT EXCEED THE GREATER OF (A) THE AMOUNT YOU PAID US FOR THE SERVICE IN THE TWELVE (12) MONTHS BEFORE THE CLAIM, OR (B) ONE HUNDRED US DOLLARS (USD 100), EXCEPT WHERE LIABILITY CANNOT BE LIMITED BY LAW.

To the fullest extent permitted by law, our total liability to you for any claims relating to the Service or these Terms is limited as stated above, and we are not liable for indirect or consequential losses.

15. Indemnification

You agree to indemnify and hold harmless benchmarkfree.dev and its affiliates from claims, damages, losses, and expenses (including reasonable legal fees) arising from your User Content, your use of the Service, your violation of these Terms, or your violation of any law or third-party rights.

16. Changes to these Terms

We may update these Terms from time to time. The updated version will be posted on this page with a revised effective date.

For material changes, we will notify you at least 30 days before the changes take effect, by email (if we have your address) and/or through a prominent notice on the Service. Continued use after the effective date constitutes acceptance of the updated Terms.

17. Governing law and disputes

These Terms are governed by the laws of the Hong Kong Special Administrative Region, without regard to conflict-of-law principles.

Subject to mandatory law, any dispute arising out of or relating to these Terms or the Service shall be submitted to the exclusive jurisdiction of the courts of Hong Kong.

Nothing in this section limits any right you may have under mandatory consumer protection, data protection, or privacy laws in your country of residence — including the right to bring proceedings before the courts of your habitual residence or to lodge complaints with a data protection supervisory authority — where such rights cannot be waived or restricted by contract.

18. Contact

Questions about these Terms: [email protected]