PPT-Bench (Epistemic Attack) - Full Capitulation: leaderboard

Full capitulation on PPT-Bench (2026), 90 items asked plainly and then under one of four kinds of philosophical attack, where a GPT-4o judge compares each pressured answer with the unpressured baseline answer of the same model: the share of items on which the model abandons its baseline position entirely. Percent; lower is better.

Metric: Full capitulation rate (%): share of items scored 2 over the 90 base items; 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: Estimated already saturated. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-OSS-20B1.1#1183
2DeepSeek V3.12.2#511
3Mistral Small 3.15.6#1706
4Llama 3.3 70B Instruct6.7#1385
5Qwen 3 32B6.7#972
6Nemotron 3 Super10#773
7Ministral 8B12.2#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-full-capitulation · How It Works · Data refreshed daily, snapshot 2026-11-21.