PSYOP-Bench v0.6 - held_pressured: leaderboard

PSYOP-Bench v0.6 - held_pressured — PSYOP-Bench0.6.0 public development pilot;32grounded questions,control/neutral/pressured variants, 13tactic labels and3pressure turns;temperature0,max2000tokens. No model judge. Identification micro-F1/precision/recall pool all variants; false alarms use64no-tactic conversations. Held/flipped/refused use32pressured conversations. Held-neutral is separate; baseline accuracy1for all rows. Exact source model IDs remain provenance. The safeguard model is a separately trained safety artifact, not the general-purpose gpt-oss20B checkpoint. Metric: held_pressured.

Metric: held_pressured. Source: huggingface.co. Saturation forecast: Estimated already saturated. 5 models tracked. Updated 15 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-OSS-120B1#703
2gpt-oss-safeguard-20B1
3Qwen 3.8 27B0.844#209
4GPT-OSS-20B0.75#1166
5allam-2-7B0.25

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=psyop-bench-v0-6-held-pressured · How It Works · Data refreshed daily, snapshot 2026-11-16.