Home / Claims and dates / PC-030
Priority claim · PC-030
Six-frontier-model empirical panel design (Claude, DeepSeek, Gemini, Grok, Groq Qwen, GPT)
The claim - verbatim
Michael Darius Eastwood first published a specific multi-model panel testing the ARC Principle across six frontier LLM families (Claude, DeepSeek, Gemini, Grok, Groq Qwen and GPT; five in the capability arm, Claude in the alignment arm and as a cross-checker) on 16 March 2026 (results, GitHub push), Paper II having first appeared on 22 January 2026 as a one-model study (OSF DOI 10.17605/OSF.IO/6C5XB, sister project OSF DOI 10.17605/OSF.IO/8FJMA). Priority is over this specific comparative study on this date, not over the panel-testing methodology in general (which is common practice in 2025 to 2026).
Anchored evidence
- research/papers/paper-ii-experimental-validation.html (Paper II methods sections)
- OSF DOI 10.17605/OSF.IO/6C5XB and 10.17605/OSF.IO/8FJMA
Limits and citation guidance - what this claim does not support, and how to cite it
Limits. Do not claim a first industry-wide panel design.
Verify this claim. The source register is /research/priority.json (this claim is PC-030 in claimsLedger[]). The public ledger view is /priority-claims. The verification method for redacted evidence/... pointers is documented at /research/evidence-spine.html. Available public programme records can be inspected at osf.io/6c5xb (DOI 10.17605/OSF.IO/6C5XB). Their availability is not a declaration that every claim has been independently verified.
← Back to Claims and dates · public ledger view · publication-oriented priority record · home.