Development

A model tops a new legal reasoning benchmark at 52%

development2026-01-25

Claim

GPT-5.2 Thinking scored a state-of-the-art 52% on the new prinzbench legal reasoning benchmark, locating obscure authority that well-paid associates often miss.

Reported metric: 52%

Reporting date: 2026-01-25 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to January 25, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

About

prinzbench

Reported in

Welcome to January 25, 2026

Actor

OpenAI

Evidence for

Referenced by

Cite or correct this record

Citation formatCitation text

A model tops a new legal reasoning benchmark at 52%
Innermost Loop KB — secondary record
Reporting date: 2026-01-25
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-01-25-prinzbench-legal-reasoning
Claim: GPT-5.2 Thinking scored a state-of-the-art 52% on the new prinzbench legal reasoning benchmark, locating obscure authority that well-paid associates often miss.
Attributed sources:
- Welcome to January 25, 2026 — https://theinnermostloop.substack.com/p/welcome-to-january-25-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.