Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.20927 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914117533564928 |
|---|---|
| author | Reed, Tom McCaslin, Tegan Righetti, Luca |
| author_facet | Reed, Tom McCaslin, Tegan Righetti, Luca |
| contents | Most frontier AI developers publicly document their safety evaluations of new AI models in model reports, including testing for chemical and biological (ChemBio) misuse risks. This practice provides a window into the methodology of these evaluations, helping to build public trust in AI systems, and enabling third party review in the still-emerging science of AI evaluation. But what aspects of evaluation methodology do developers currently include -- or omit -- in their reports? This paper examines three frontier AI model reports published in spring 2025 with among the most detailed documentation: OpenAI's o3, Anthropic's Claude 4, and Google DeepMind's Gemini 2.5 Pro. We compare these using the STREAM (v1) standard for reporting ChemBio benchmark evaluations. Each model report included some useful details that the others did not, and all model reports were found to have areas for development, suggesting that developers could benefit from adopting one another's best reporting practices. We identified several items where reporting was less well-developed across all model reports, such as providing examples of test material, and including a detailed list of elicitation conditions. Overall, we recommend that AI developers continue to strengthen the emerging science of evaluation by working towards greater transparency in areas where reporting currently remains limited. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20927 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | What do model reports say about their ChemBio benchmark evaluations? Comparing recent releases to the STREAM framework Reed, Tom McCaslin, Tegan Righetti, Luca Computers and Society Most frontier AI developers publicly document their safety evaluations of new AI models in model reports, including testing for chemical and biological (ChemBio) misuse risks. This practice provides a window into the methodology of these evaluations, helping to build public trust in AI systems, and enabling third party review in the still-emerging science of AI evaluation. But what aspects of evaluation methodology do developers currently include -- or omit -- in their reports? This paper examines three frontier AI model reports published in spring 2025 with among the most detailed documentation: OpenAI's o3, Anthropic's Claude 4, and Google DeepMind's Gemini 2.5 Pro. We compare these using the STREAM (v1) standard for reporting ChemBio benchmark evaluations. Each model report included some useful details that the others did not, and all model reports were found to have areas for development, suggesting that developers could benefit from adopting one another's best reporting practices. We identified several items where reporting was less well-developed across all model reports, such as providing examples of test material, and including a detailed list of elicitation conditions. Overall, we recommend that AI developers continue to strengthen the emerging science of evaluation by working towards greater transparency in areas where reporting currently remains limited. |
| title | What do model reports say about their ChemBio benchmark evaluations? Comparing recent releases to the STREAM framework |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2510.20927 |