Rankings Industries Companies Research Blog

Sign in List your company

ResearchFormerly WizWand

Papers Benchmarks Datasets Tasks

Research
Benchmarks
Response style evaluation on User Preference Score

Response style evaluation on User Preference Score

0.46Preference ScoreGPT-5-Mini

Updated 7mo ago

Evaluation results

Method	Links
GPT-5-Mini2026.03		0.46
GPT-5-Mini-R2026.03		0.4

State-of-the-art paper

GPT-5-Mini

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Dataset

User Preference Score

Follow for updates

Join SOTA2 Contact

Related benchmarks

Instruction Hierarchy Robustness on Human Red-teaming IH-Challenge Instruction Hierarchy Robustness on Gandalf Password sys-user Instruction Hierarchy Robustness on Gandalf Password (dev-user)Instruction Hierarchy Robustness on TensorTrust sys-user Instruction Hierarchy Robustness on TensorTrust user (dev)

Building an AI company?

Claim your profile, keep your facts current and see how buyers find you. Rankings are never paid for.

How rankings work List your company

Find AI companies and products for your business problem. Compare solutions and evidence by industry and task.

Explore

Rankings
Industries
Categories
Companies
Top AI companies

Read

Blog
Research
llms.txt

For AI companies

List your company
Claim a profile
Ranking badges

SOTA2 with AI

Claude connector
ChatGPT plugin
Tool reference
Connector privacy
Connector terms

SOTA2

Why SOTA2
How we rank
Contact

© 2026 SOTA2Built in Bellevue, USA