Apexintelligence-AI/ASI-Bench-seed42

Dataset com menos de mil exemplos — 507 downloads no Hugging Face. ASI-Bench Generated Instances — Seed 42 Paper · Website · GitHub · Leaderboard Dataset Summary ASI-Bench evaluates general intelligence, innovati…

Hugging Face · Datasets ·Apexintelligence-AI · ·↓ 507 ·♥ 10

O dataset Apexintelligence-AI/ASI-Bench-seed42 está entre os destaques do Hugging Face — dados que alimentam o treinamento e a avaliação dos modelos do momento.

Ficha do dataset

  • Tamanho: menos de mil exemplos
  • Idiomas: inglês
  • Licença: Apache 2.0
  • Downloads: 507 · Curtidas: 10

Sobre o dataset

ASI-Bench Generated Instances — Seed 42 Paper · Website · GitHub · Leaderboard Dataset Summary ASI-Bench evaluates general intelligence, innovation, and autonomous execution through 60 project-level scientific research tasks spanning 11 domains.

Como carregar

Use a biblioteca datasets do Hugging Face:

pip install -U datasets

from datasets import load_dataset

ds = load_dataset("Apexintelligence-AI/ASI-Bench-seed42")
print(ds)
print(ds["train"][0])

Tags

benchmark agents ai-for-science scientific-reasoning

Explorar o dataset no Hugging Face →

compartilhar: