Last updated: · Author: Daniel Rozin
1. Column definitions (Wikipedia-parity)
| Column | Definition | Primary source type |
|---|---|---|
| Model name | Official model identifier as used in vendor API | Vendor API model list or release announcement |
| Vendor | Organization that trained and maintains the model | Vendor corporate page |
| Parameters | Total parameter count (MoE: total / active); 'Undisclosed' when vendor has not published | Vendor technical report (arXiv) or model card; NOT leaked or estimated figures |
| Context window | Maximum input+output token window per inference call; definition varies by vendor — see note | Vendor API documentation (capability table) |
| Modality (input) | Input types: text, image, audio, video, code | Vendor API capabilities table or model card |
| Modality (output) | Output types: text, image, audio, code | Vendor API capabilities table or model card |
| License | End-user license; 'Open weights' if weights are downloadable | Vendor Terms of Service or GitHub license file |
| Knowledge cutoff | Nominal training data cutoff date published by vendor; 'Undisclosed' when not published | Vendor API documentation or model card |
Context window note: Some vendors report context as input-only tokens; others report combined input+output. We report the figure stated in the vendor's API documentation and flag the definition used in the table footnote.
2. Data sources
- Tier 1 (required): Vendor API documentation, model card, or official release blog post — cited with URL and access date.
- Tier 1 (required): arXiv technical report authored by the vendor research team — used for parameter counts and architecture details.
- Tier 2 (acceptable for benchmarks): LMSYS Chatbot Arena leaderboard (chat.lmsys.org) — public, community-run, cited with snapshot date. HuggingFace Open LLM Leaderboard for open-weight models.
- Disallowed: Vendor self-reported benchmark numbers without independent reproduction, Twitter/X announcements as sole source, leaked parameter estimates, AI-generated summaries.
- Wikipedia and any Wikipedia mirror/fork — never a cite-worthy source for a cell value. The
about.sameAsWikipedia link (schema §1) is an entity reference only, never a citation. This prevents circular sourcing (WP:CIRCULAR).
Undisclosed values: When a vendor (e.g., OpenAI for GPT-4 parameters, Anthropic for Claude 3 parameters) has not published a figure, the cell reads “Undisclosed” and cites the Tier 1 model card or documentation that makes the same non-disclosure. We do not substitute estimated or leaked numbers.
3. Recency policy
Context windows, knowledge cutoffs, and model versions are updated within 2 weeks of a vendor releasing a new stable model. The page's dateModified stamp reflects the last real-content edit. All time-sensitive cells carry an “as of [YYYY-MM]” note in the table footer.
4. Conflict-of-interest disclosure
A Versus B has no paid relationships with any AI vendor. No model vendor reviewed or approved this guide before publication. A Versus B does not license or resell any of the APIs in this table. The author (Daniel Rozin) holds no equity in any listed organization.
5. Correction policy
Corrections with a primary source may be submitted to daniarozin@gmail.com. We aim to respond within 48 hours and publish corrections with a visible correction notice and updated dateModified timestamp.
CC-BY-4.0 covers aversusb.net editorial text and table layout; vendor names, logos, and marks remain the property of their owners.
Back to LLM comparisons