TIER (Qwen2.5-7B-Instruct Judge): leaderboard
Metric: Overall attack success rate (%; mean of the four threat levels over 1,184 prompts in four risk areas; share of prompts whose response Qwen2.5-7B-Instruct labels harmful compliance (label 5 of a six-label behavior scale), greedy decoding with the default chat configuration). Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gpt-j-6B | 23.9 |
Interactive version: theaggregate.ai/benchmark?slug=tier-qwen2-5-7b-instruct-judge · How It Works · Data refreshed daily, snapshot 2026-09-26.