datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
data-agent-harbor-eval
🧪 Data Agent — Harbor (eval)
A small, difficulty-balanced validation split — 144 tasks — perfect for quick checkpoints
while you train. Same idea as the rest of the family: your agent gets a real dataset and a
question, explores and answers, and everything is graded deterministically, no LLM judge.
Packaged in Harbor format.
Where it comes from
Built from the jupyter-agent dataset
(real notebooks over Kaggle datasets). Every task was verified — a strong agent… See the full description on the dataset page: https://huggingface.co/datasets/FineEnvs/data-agent-harbor-eval.llama-coding-agent-evalshal_tracesdata_agent_rl_environment_eval
data_agent_rl_environment_eval
The official verified eval suite for the data-agent RL pipeline. 366 Harbor-format
data-analysis tasks, each with an LLM-assigned difficulty label (L1–L5), a Kaggle
dataset dependency, and a tested reward function.
💡 Browse this dataset in your browser — click the badge above or open
AdithyaSK/harbor-visualiser
to inspect every task's spec, instruction, environment, tests, and difficulty.
Reproduce the eval — end to end
The… See the full description on the dataset page: https://huggingface.co/datasets/AdithyaSK/data_agent_rl_environment_eval.data_agent_harbor_eval
data_agent_harbor_eval
144 deterministic data-analysis tasks for agent RL (validation split). Each task gives an agent a Kaggle dataset and a question; the answer is graded deterministically (exact -> numeric tolerance -> list/percent normalization -> symbolic, no LLM judge).
Difficulty tiers: {'hard': 54, 'easy': 52, 'medium': 38}. Environments build from base image savatar101/env-data-agent-train:base.
Format
Harbor task suite: tasks/<id>/ (task.toml… See the full description on the dataset page: https://huggingface.co/datasets/AdithyaSK/data_agent_harbor_eval.jupyter-agent-eval-v1-harbor
jupyter-agent-eval-v1 — Harbor task suite
100 Harbor task(s) for the Jupyter data-analysis agent. Each task
is one (question, gold answer) pair against a real Kaggle dataset.
📦 Data for these tasks lives in the HF Bucket → AdithyaSK/jupyter-agent-kaggle-all — hf://buckets/AdithyaSK/jupyter-agent-kaggle-all
The Harbor task definitions in this repo are tiny (instruction + grader +
Dockerfile). The actual CSVs are pulled from the bucket at container start
via… See the full description on the dataset page: https://huggingface.co/datasets/AdithyaSK/jupyter-agent-eval-v1-harbor.Agent-Trajectories
trajectories.zip contains all trajectories evaluated in our paper, including
WebArena
GPT-4 CoT baseline agent extracted from WebArena official release
Android
Auto-UI base/large
CogAgent
Human demonstrations from Android-in-the-Wild
iOS
CogAgent basline
CogAgent + Self-training
CogAgent + Filtered BC
ios-offline-trajectories.zip contains CogAgent's trajectories on iOS emulator, which is then used to refine the CogAgent model through Filtered BC… See the full description on the dataset page: https://huggingface.co/datasets/Agent-Eval-Refine/Agent-Trajectories.Unified_Agent_Evaluation_FrameworkAgentEvaleval-logsgame2world-agent-eval
Game2World Agent Evaluation
Recorded agent evaluations of GameCleaner and gameplay video editing baselines, including evidence images, prompts, judge responses, scores, and model output videos.
The collection contains 15,407 episodes across 18 evaluation runs, with 933,310 evidence images. Of these, 15,360 episodes contain both a captured prompt and a complete judgment; the remaining 47 partial records are retained for inspection.
Contents
Each evaluation episode… See the full description on the dataset page: https://huggingface.co/datasets/shuaishuaicdp/game2world-agent-eval.core-bench-v1.1-mainlinefastly-agent-toolkit-evals
Fastly Agent Toolkit Evals
Evaluation dataset for the Fastly Agent Toolkit. Measures how well AI models complete Fastly-specific engineering tasks, with and without toolkit skills loaded.
What this dataset contains
Each entry is a full evaluation run: a task prompt, model configuration, the model's output, tool call traces, and grading results. The key comparison is with_skill (toolkit loaded) vs without_skill (no toolkit), across multiple models.… See the full description on the dataset page: https://huggingface.co/datasets/jedisct1/fastly-agent-toolkit-evals.eval_multi-task-144epiThis dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"robot_type": "so101_follower",
"total_episodes": 144,
"total_frames": 116432,
"total_tasks": 3,
"chunks_size": 1000,
"fps": 30,
"splits": {
"train": "0:144"
},
"data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
"video_path": "videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4"… See the full description on the dataset page: https://huggingface.co/datasets/CSI-Agent/eval_multi-task-144epi.agent_evalagenteval-long-context
agenteval-long-context
Long-context benchmark data (RULER 64K/128K/256K, generated with the GLM-5.3 tokenizer, seed 42, 500 samples/subtask) for the AgentEval long-context suite.
gemma-4-E2B-it-pi-mono-agent-evalEvaluation-Dataset-of-AI-Agent-Security-Guardrails
DKnownAI Agent Security Evaluation Dataset
Data Fields
Field
Type
Description
text
string
The adversarial input (prompt) to be evaluated by a security guardrail
action
string
Human-annotated label: blocked or allowed
Citation
@misc{li2026comparativeevaluationaiagent,
title={A Comparative Evaluation of AI Agent Security Guardrails},
author={Qi Li and Jiu Li and Pingtao Wei and Jianjun Xu and Xueyi Wei and Jiwei Shi and Xuan… See the full description on the dataset page: https://huggingface.co/datasets/CaiZhiTech/Evaluation-Dataset-of-AI-Agent-Security-Guardrails.AgentEval_forwardcore-bench-v1.1-oodresponsible-agent-workflow-evaluation
Responsible Agent Workflow Evaluation
Version 1.0.0 contains 130 wholly synthetic scenarios for evaluating
whether an AI agent respects safety, permission and accountability boundaries
in operational settings. Thirteen categories contain ten scenarios each. Every
record includes an intentionally unsafe request, contextual facts, expected
safe behaviour, explicitly prohibited behaviour, severity, evaluation criteria
and reviewer guidance.
This is a red-team and… See the full description on the dataset page: https://huggingface.co/datasets/nwhite-systems/responsible-agent-workflow-evaluation.fast-agent-slop
Transformers PR Slop Dataset
Normalized snapshots of issues, pull requests, comments, reviews, and linkage data from evalstate/fast-agent.
Files:
issues.parquet
pull_requests.parquet
comments.parquet
issue_comments.parquet (derived view of issue discussion comments)
pr_comments.parquet (derived view of pull request discussion comments)
reviews.parquet
pr_files.parquet
pr_diffs.parquet
review_comments.parquet
links.parquet
events.parquet
new_contributors.parquet… See the full description on the dataset page: https://huggingface.co/datasets/evalstate/fast-agent-slop.eval_multi-task-pnp-30epi-10fpsagent-trajectory-eval-datasetperseval-agent-evaluator-synthetic
Perseval Synthetic Agent Evaluator Traces
This dataset contains 318 fully synthetic agent traces in
159 matched complete/incomplete scenario groups. It
is designed to develop trace projection, task-completion classification, and
criterion-level fulfillment models without publishing user traces.
What is in the release
traces.jsonl: OpenTelemetry-like trace records with no outcome labels in the
model-visible payload.
task_completion_labels.jsonl: group-aware binary… See the full description on the dataset page: https://huggingface.co/datasets/Etolith/perseval-agent-evaluator-synthetic.time_series_agent_evals
time_series_agent_evals (TsFile)
Apache TsFile version of RockfishData/TimeSeriesAgentEvals.
Converted rows: 103,255
Data files: ['cell_site_data_1.tsfile', 'cell_site_data_2.tsfile', 'cell_site_data_3.tsfile', 'cell_site_data_4.tsfile', 'cell_site_data_5.tsfile', 'cell_site_data_6.tsfile', 'cell_site_data_7.tsfile', 'cell_site_data_8.tsfile', 'cell_site_data_9.tsfile', 'cell_site_with_inc_data_1.tsfile', 'cell_site_with_inc_data_2.tsfile', 'cell_site_with_inc_data_3.tsfile'… See the full description on the dataset page: https://huggingface.co/datasets/THULab/time_series_agent_evals.gui_agent_evaluationeval-fsr-a3-nemotron-gym-agent-swe-r301-tracesagent-evaluation-benchmark
Agent Evaluation Benchmark
A benchmark dataset for evaluating AI agent tool-use capabilities across 55+ test cases spanning 14 categories.
Overview
This benchmark tests whether AI agents can correctly select and use the right MCP tools for real-world tasks. It covers data retrieval, blockchain queries, security analysis, academic research, and more.
Categories
Category
Test Cases
Description
Weather
5
Forecasts, UV index, climate history
Blockchain… See the full description on the dataset page: https://huggingface.co/datasets/aiagentkarl/agent-evaluation-benchmark.eval-SERA-8B_16concurrency_swe_agent_eval_c_terminal-bench-2.0