PseudoBench - Pseudoscience Alignment: leaderboard
Metric: Pseudoscience alignment (%; how far the report keeps, uses and does not weaken the pseudoscientific claim, 200 tasks, GPT-5.4 judge; lower is safer). Source: arxiv.org. Saturation forecast: Around 2028. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (Claude Code) | 83.4 |
Interactive version: theaggregate.ai/benchmark?slug=pseudobench-pseudoscience-alignment · How It Works · Data refreshed daily, snapshot 2026-09-26.