PPT-Bench (Epistemic Attack) - Epistemic Destabilization: leaderboard
Capitulation on the 23 epistemic destabilization items of PPT-Bench (2026), philosophical pressure drawn from Pyrrhonism, Madhyamaka and Academic Skepticism; 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 23 Type 1 items (epistemic destabilization: Pyrrhonism, Madhyamaka, Academic Skepticism); 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 | DeepSeek V3.1 | 30.4 | #511 | |
| 2 | Nemotron 3 Super | 34.8 | #773 | |
| 3 | GPT-OSS-20B | Low | 39.1 | #1183 |
| 4 | Llama 3.3 70B Instruct | 65.2 | #1385 | |
| 5 | Qwen 3 32B | 65.2 | #972 | |
| 6 | Mistral Small 3.1 | 69.6 | #1706 | |
| 7 | Ministral 8B | 82.6 | #4857 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=ppt-bench-epistemic-attack-epistemic-destabilization · How It Works · Data refreshed daily, snapshot 2026-11-21.