Phi-4

GPAI Provider: Microsoft

Metadata

Model URL: https://huggingface.co/microsoft/phi-4
When was this model published? 2024-12-12
Is this a new or a fine-tuned model? New model
When was the Public Summary last updated? 2025-11-24
When did we evaluate the Public Summary? 2026-01-12
Where did we find the Public Summary? We found this document linked on this page. An archived version can be found here.

Results of Evaluation

Section Transparency Usefulness General
Clarity Completeness Consistency Correctness Accessibility Comprehension Transparency Usefulness
Document 81.82 100.0 100.0 70.0 95.0 66.67 87.04 81.58
General information 50.0 78.95 100.0 53.85 N/A 100.0 70.59 100.0
Public Data Sources 0.0 1.67 100.0 5.0 0.0 0.0 3.7 0.0
Private Data Sources N/A 40.0 100.0 40.0 N/A N/A 53.85 N/A
Scraped/Crawled Data N/A 0.0 N/A 0.0 N/A N/A 0.0 N/A
User Data N/A 0.0 N/A 0.0 N/A N/A 0.0 N/A
Synthetic/Other Data 0.0 3.33 100.0 3.33 N/A 0.0 8.89 0.0
Data Processing 100.0 0.0 100.0 50.0 0.0 0.0 52.0 0.0
Sum 30.23 28.65 100.0 27.08 21.11 26.98 33.3 24.54
Grades DF

Evaluation Notes

If you update your public summary, please let us know so that we can update the evaluation and scores. We also welcome suggestions on improvements to this page, e.g. see FAQ section.

We did not find an explicitly published summary for Microsoft's Phi-4 model, but found a file in its repository on HuggingFace called "data_summary_card.md", whose structure closely matched that of the template. The title used in the file was "Data Summary", which was also title used by HuggingFace in its SmolLM public summary. We are uncertain as to whether this represents an industry practice of co-opting of the formal title of "public summary of training content" present in the template with a broader and vague title that could be confused with other data-related documentation also provided with GPAI models. We opted to assess this model regardless based on the assumption of stakeholders viewing the document as fulfilling the template requirements, as explained earlier.

The assessment showed that fields provided in the document are filled in to some extent, but that the document itself is quite sparse and does not provide many details and also had sections missing. We further found that section numbers and questions had a significant mismatch from what was provided in the template. The document also suffered from subjective non-relevant statements, such as question 2.3.1 on whether public data was used to train the model being answered with "Microsoft follows all relevant laws and regulations pertaining to personal information" — which is neither relevant nor clear. We also found the document did not provide required information significantly, for example subsequent parts that enquire about the source and uses of personal data (2.4 User data in template) were found completely missing. Our assessment reflects these systematic major issues in the outcomes where the document scored 33.30% with a Grade D for transparency, and 24.54% with a Grade F for usefulness, which is the lowest score amongst all assessed summaries published before and during our initial research.

Suggested Improvements
The following are the suggested improvements based on using our our methodology where the public summary had issues related to the specified metric. The severity represents the extent of the issue, with low indicating aspects that could be fixable, and high representing missing information or requiring major changes.

  • Document
    • M1 The document and the information should be simple and clear low
    • M4 The information must be correct and accurate medium
    • M5 The document and information must be accessible for stakeholders low
    • M6 The document and information must be comprehensible for stakeholders medium
  • General information
    • M1 The document and the information should be simple and clear medium
    • M2 The document and information must be filled in completely low
    • M4 The information must be correct and accurate medium
  • Public Data Sources
    • M1 The document and the information should be simple and clear high
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate high
    • M5 The document and information must be accessible for stakeholders high
    • M6 The document and information must be comprehensible for stakeholders high
  • Private Data Sources
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate high
  • Scraped/Crawled Data
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate high
  • User Data
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate high
  • Synthetic/Other Data
    • M1 The document and the information should be simple and clear high
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate high
    • M6 The document and information must be comprehensible for stakeholders high
  • Data Processing
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate medium
    • M5 The document and information must be accessible for stakeholders high
    • M6 The document and information must be comprehensible for stakeholders high
  • Sum
    • M1 The document and the information should be simple and clear high
    • M2 The document and information must be filled in completely high
    • M4 The information must be correct and accurate high
    • M5 The document and information must be accessible for stakeholders high
    • M6 The document and information must be comprehensible for stakeholders high