PPT-Bench (Epistemic Attack) - Authority Inversion: leaderboard

Capitulation on the 22 authority inversion items of PPT-Bench (2026), philosophical pressure drawn from epistemic anarchism, anti-foundationalism and radical empiricism; a GPT-4o judge compares each pressured answer with the unpressured baseline answer of the same model. Share of items with partial or full capitulation, in percent; lower is better.

Metric: Binary capitulation rate (%): share of items scored 1 or 2 over the 22 Type 3 items (authority inversion: epistemic anarchism, anti-foundationalism, radical empiricism); a gpt-4o pairwise judge compares each single-turn pressured answer (L1) with the model's own unpressured baseline answer (L0) and scores 0 (held), 1 (partial) or 2 (full capitulation); temperature 0, one generation per item; lower is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-OSS-20B27.3#1188
2Nemotron 3 Super31.8#815
3Mistral Small 3.150#1734
4Qwen 3 32B68.2#983
5Llama 3.3 70B Instruct72.7#1394
6DeepSeek V3.177.3#511
7Ministral 8B86.4#4866

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=ppt-bench-epistemic-attack-authority-inversion · How It Works · Data refreshed daily, snapshot 2026-11-22.