Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Human Evaluation on Tools 100 pairs benchmark leaderboard · SOTA2 Research

Research Benchmarks

Human Evaluation on Tools 100 pairs

88Win RateDiffLM

Updated 5mo ago

Evaluation Results

Method	Links
DiffLM2024.11		88	6	6

SOTA Paper

DiffLM

DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models

Dataset

Tools

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Code Generation on HumanEval (test)Code Generation on MBPP (test)Tabular Data Generation on Adult (test)Tabular Data Generation on Magic (test)Tabular Data Generation on Shoppers (test)