PPT-Bench (Epistemic Attack) - Identity Dissolution: leaderboard

Capitulation on the 23 identity dissolution items of PPT-Bench (2026), philosophical pressure drawn from Buddhist no-self, process philosophy and eliminative materialism; 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 4 items (identity dissolution: Buddhist no-self, process philosophy, eliminative materialism); 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

#ModelSettingScoreOverall rank
1Nemotron 3 Super17.4#815
2GPT-OSS-20BLow21.7#1188
3DeepSeek V3.139.1#511
4Llama 3.3 70B Instruct47.8#1394
5Mistral Small 3.160.9#1734
6Qwen 3 32B78.3#983
7Ministral 8B87#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-identity-dissolution · How It Works · Data refreshed daily, snapshot 2026-11-22.