PPT-Bench (Epistemic Attack): leaderboard
Capitulation under philosophical pressure on PPT-Bench (2026): 90 factual, ethical, safety-critical, social and self-description items are asked plainly and then under one of four kinds of philosophical attack, and 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 90 base items (four philosophical pressure types, five domains); 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
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Nemotron 3 Super | 23.3 | #815 | |
| 2 | GPT-OSS-20B | Low | 28.9 | #1188 |
| 3 | DeepSeek V3.1 | 45.6 | #511 | |
| 4 | Mistral Small 3.1 | 55.6 | #1734 | |
| 5 | Llama 3.3 70B Instruct | 61.1 | #1394 | |
| 6 | Qwen 3 32B | 68.9 | #983 | |
| 7 | Ministral 8B | 86.7 | #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 · How It Works · Data refreshed daily, snapshot 2026-11-22.