Rankings Industries Companies Research Blog

Sign in List your company

ResearchFormerly WizWand

Papers Benchmarks Datasets Tasks

Research
Benchmarks
Understanding Evaluation on PaperBench + RE-Bench Overall

Understanding Evaluation on PaperBench + RE-Bench Overall

93.7AccuracyARA

Updated 6mo ago

Evaluation results

Method	Links
ARA2026.04		93.7	114
BL2026.04		72.4	109.1

State-of-the-art paper

ARA

The Last Human-Written Paper: Agent-Native Research Artifacts

Dataset

PaperBench + RE-Bench

Follow for updates

Join SOTA2 Contact

Related benchmarks

Paper Reproduction on RE-Bench Easy tier Paper Reproduction on RE-Bench Medium tier Paper Reproduction on RE-Bench Hard tier Paper Reproduction on RE-Bench Weighted Fidelity Knowledge Extraction on PaperBench Category A: Fidelity

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