Tag
Explore by tags
Provides labeled movie-review data for binary sentiment classification: 25,000 training and 25,000 test examples, plus 50,000 unlabeled reviews for unsupervised or semi-supervised use. Labels reflect strong polarity (positive ≥7, negative ≤4) and the set is a widely used NLP benchmark.
Provides about 100,000 crowd‑written question–answer pairs from Wikipedia where each answer is a text span in the passage, used to train and evaluate extractive question‑answering models. Includes train/validation splits, span offsets, Parquet format, CC BY‑SA 4.0.
A multi-task English NLU benchmark for evaluating models across nine tasks (acceptability, sentiment, paraphrase, similarity, and various NLI setups), with a diagnostic evaluation set and an online leaderboard to compare generalization and transfer learning.
Tests whether browser agents complete 812 tasks across realistic shopping, forum, development, and content-management sites. Evaluates final outcomes rather than matching a reference sequence of clicks.
A public dataset of one million real-world conversations with 25 LLMs, including conversation text, model name, detected language tags, and OpenAI moderation outputs — useful for studying prompt distributions, safety/moderation, and training/evaluating instruction-following models.
Benchmark for evaluating general AI assistants with 466 short, real-world questions that require tool use, multimodality and reasoning; provides a public dev set and a withheld test set used for leaderboard evaluation.
A multiple-choice benchmark for evaluating LLM understanding in Traditional Chinese across 66 subjects (elementary to professional). Contains ~22K verified questions covering STEM, humanities, social sciences and Taiwan-specific topics, with standardized splits and model leaderboards under an MIT license.
Tests whether web agents can use visual evidence to finish 910 tasks across shopping, classifieds, and social forums. Execution-based checks distinguish successful actions from plausible explanations.
Lets language-model agents compose tools through executable Python and revise actions from interpreter feedback. Evaluates 17 models and releases 7,000 interaction trajectories for training agents that can debug their own code.
Tests whether agents can finish 369 tasks in real desktop applications, using executable checks of the final state. The original study found a wide gap between agent and human success rates.
Provides manually curated Japanese instruction pairs (questions and safe reference answers) for improving LLM output safety, covering broad harm categories and regionally sensitive cases. Includes English meta-tags and standard splits for benchmarking and fine-tuning.
A 12K-question multiple-choice benchmark that raises difficulty by expanding choices to ten and adding reasoning-focused problems. Designed for robust LLM evaluation with cross-domain coverage, expert curation, and emphasis on chain-of-thought performance.