← Leaderboard
OpenAI
Eligible: the provider-reported training data/knowledge cutoff is before the earliest decision we used to test; a month-only cutoff counts as the first day of that month.Cutoff: June 1, 2024 (knowledge cutoff)GPT-4.1
Micro BrierMicro Brier is the headline metric: squared error of each dismissal forecast, averaged over all claim-defendant units. Lower is better; always answering 50% scores 0.25.
0.6051
Reference model · not ranked
Equal-case Brier
0.5752
Reference model · not ranked
Unit accuracy
39.0%
Reference model · not ranked
An older reference model
GPT-4.1 is an older, non-reasoning model run on the same full record and harness. It is kept as a reference rather than ranked with current models. It mostly answered 0% or 100%, and its forecasts show no ranking signal.
Statistical comparison coverage
Included in the paired significance analysis.
Analysis and reproducible inputs →Statistically distinguishable differences
- Worse than Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5, Gemini 3.1 Pro Preview, GPT-5.6 Luna, GPT-5.6 Sol, GPT-6.1 Sol, GPT-6 Luna, GPT-6 Sol, Grok 4.7, and Muse Wonder on Micro Brier, Equal-case Brier, and Unit accuracy.