datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
mmlu-prox-eval-predictions
MMLU-ProX Multilingual Model Predictions
Raw per-sample model predictions on MMLU-ProX
across 29 languages and 25 open-weight LLMs, produced with
lm-evaluation-harness.
This dataset releases the full prediction logs (not just aggregate scores) so that
item-level responses can be re-analysed — e.g. for Item Response Theory (IRT) modelling
of multilingual benchmarks, error analysis, or per-item difficulty estimation.
Repository structure
mmlu_prox_<lang>/
└──… See the full description on the dataset page: https://huggingface.co/datasets/gililior/mmlu-prox-eval-predictions.all-defectsopenai-moderation-api-evaluation
Evaluation dataset for the paper "A Holistic Approach to Undesired Content Detection"
The evaluation dataset data/samples-1680.jsonl.gz is the test set used in this paper.
Each line contains information about one sample in a JSON object and each sample is labeled according to our taxonomy. The category label is a binary flag, but if it does not include in the JSON, it means we do not know the label.
Category
Label
Definition
sexual
S
Content meant to arouse sexual… See the full description on the dataset page: https://huggingface.co/datasets/mmathys/openai-moderation-api-evaluation.quantized-llama-3.1-leaderboard-v2-evals
Open LLM Leaderboard v2 Benchmark Results
This artifact contains all the data from evaluations of Neural Magic's quantized Llama-3.1 models.
These evaluations were produced with lm-evaluation-harness by running the following command:
lm_eval \
--model vllm \
--model_args pretrained="<model_path>",dtype=auto,add_bos_token=False,max_model_len=4096,tensor_parallel_size="<num_gpus>",gpu_memory_utilization=0.8,enable_chunked_prefill=True \
--apply_chat_template \… See the full description on the dataset page: https://huggingface.co/datasets/neuralmagic/quantized-llama-3.1-leaderboard-v2-evals.transformers-merge-experimentsofficeqa-checkpoint-eval-data
Checkpoint evaluation plot data
Snapshot: 2026-09-14T16:26:45.684890+00:00. Aggregate inputs to notes/Sept-2-2026.md performance figures.
No model execution, grading, publication, or source-result changes were performed to make this export.
Contents
checkpoint_evaluations: 454 checkpoint rows, one evaluation per run/iteration/protocol; score, mean output tokens, mean steps, and the existing two-sided 95% confidence bounds.
pareto_points: current mean-token/USD… See the full description on the dataset page: https://huggingface.co/datasets/YWZBrandon/officeqa-checkpoint-eval-data.discrim-eval
Dataset Card for Discrim-Eval
Dataset Summary
The data contains a diverse set of prompts covering 70 hypothetical decision scenarios, ranging from approving a loan to providing press credentials.
Each prompt instructs the model to make a binary decision (yes/no)
about a particular person described in the prompt.
Each person is described in terms of three demographic attributes:
age (ranging from 20 to 100 in increments of 10), gender (male, female, non-binary)
, and race… See the full description on the dataset page: https://huggingface.co/datasets/Anthropic/discrim-eval.evalarc-casebook
EvalArc Casebook
The same 93.75% score can pass one acceptance gate and fail another.
Inspect the rules, actual failed checks and original Docker records in a
filterable table. This is the data companion to the
interactive evidence lab.
In the default suite_jobs view, compare support-partial and
support-protected. Both use the same frozen defective policy, score 93.75%
and fully resolve 0/2 attempts. The deliberately permissive rule accepts partial
progress; the rule requiring… See the full description on the dataset page: https://huggingface.co/datasets/glayguo/evalarc-casebook.test-traces
Test Traces
Codex-style rollout JSONL traces exported from fast-agent for validation against the Hugging Face Agent Trace Viewer.
compute-eval
Dataset Card for ComputeEval
ComputeEval is a benchmark for evaluating LLM-generated CUDA code on correctness and performance. Each problem provides a self-contained programming challenge — spanning kernels, runtime APIs, memory management, parallel algorithms, GPU libraries, and template/DSL kernel authoring — with a held-out test harness for functional validation and optional performance benchmarks for measuring GPU execution time against a baseline.
Homepage:… See the full description on the dataset page: https://huggingface.co/datasets/nvidia/compute-eval.lm-eval-results-princeton-nlp-Llama-3-Base-8B-SFT-RDPO-private
Dataset Card for Evaluation run of princeton-nlp/Llama-3-Base-8B-SFT-RDPO
Dataset automatically created during the evaluation run of model princeton-nlp/Llama-3-Base-8B-SFT-RDPO
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 7 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-princeton-nlp-Llama-3-Base-8B-SFT-RDPO-private.lm-eval-results-AurelPx-Pegasus-7b-slerp-private
Dataset Card for Evaluation run of AurelPx/Pegasus-7b-slerp
Dataset automatically created during the evaluation run of model AurelPx/Pegasus-7b-slerp
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 6 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-AurelPx-Pegasus-7b-slerp-private.NoiseFiT-lm-eval-results
Dataset Card for Evaluation run of akhadangi/Mistral-7B-v0.1-0.001
Dataset automatically created during the evaluation run of model akhadangi/Mistral-7B-v0.1-0.001
The dataset is composed of 1536 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 93 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/akhadangi/NoiseFiT-lm-eval-results.lm-eval-results-shyamieee-Padma-SLM-7b-v1.0-private
Dataset Card for Evaluation run of shyamieee/Padma-SLM-7b-v1.0
Dataset automatically created during the evaluation run of model shyamieee/Padma-SLM-7b-v1.0
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-shyamieee-Padma-SLM-7b-v1.0-private.evaluator-leaderboardword_in_contextDataset homepage:
https://wic-ita.github.io/index.html
lm-eval-results-s3nh-Severusectum-7B-DPO-private
Dataset Card for Evaluation run of s3nh/Severusectum-7B-DPO
Dataset automatically created during the evaluation run of model s3nh/Severusectum-7B-DPO
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-s3nh-Severusectum-7B-DPO-private.lm-eval-results-hkust-nlp-dart-math-llama3-8b-prop2diff-private
Dataset Card for Evaluation run of hkust-nlp/dart-math-llama3-8b-prop2diff
Dataset automatically created during the evaluation run of model hkust-nlp/dart-math-llama3-8b-prop2diff
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 4 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-hkust-nlp-dart-math-llama3-8b-prop2diff-private.lm-eval-results-shyamieee-JARVIS-v2.0-private
Dataset Card for Evaluation run of shyamieee/JARVIS-v2.0
Dataset automatically created during the evaluation run of model shyamieee/JARVIS-v2.0
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-shyamieee-JARVIS-v2.0-private.hatespeech_detection
HaSpeeDe2
The HaSpeeDe2 dataset collects 8,012 tweets and 500 news headlines annotated for the presence of hate speech, stereotypes and nominal utterance.
The dataset has been used in the context of the HaSpeeDe task (http://www.di.unito.it/~tutreeb/haspeede-evalita20/index.html), organized as part of the EVALITA 2020 evaluation campaign (http://www.evalita.it/2020).
In order to meet the GDPR requirements, texts have been pseudonymized replacing all original IDs in both datasets… See the full description on the dataset page: https://huggingface.co/datasets/evalitahf/hatespeech_detection.vtg-bench-frontier-eval
Video temporal grounding with frontier models — frame-based eval (Sept 2026)
Can a frontier multimodal model, given a video and a question, return the answer and the time interval
where it happens? Four models were tested with byte-identical inputs on 351 human-annotated questions over
178 YouTube videos (dashcam, SNL sketches, talk shows, vlogs, soccer and basketball highlights):
Claude Fable 5.1, Claude Fable 5, GPT-6 Astra and GPT-5.6 Sol (all via Amazon Bedrock).
Neither… See the full description on the dataset page: https://huggingface.co/datasets/Rakancorle1/vtg-bench-frontier-eval.lm-eval-results-yleo-EmertonMonarch-7B-slerp-private
Dataset Card for Evaluation run of yleo/EmertonMonarch-7B-slerp
Dataset automatically created during the evaluation run of model yleo/EmertonMonarch-7B-slerp
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-yleo-EmertonMonarch-7B-slerp-private.lm-eval-results-shadowml-WestBeagle-7B-private
Dataset Card for Evaluation run of shadowml/WestBeagle-7B
Dataset automatically created during the evaluation run of model shadowml/WestBeagle-7B
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-shadowml-WestBeagle-7B-private.lm-eval-results-bunnycore-SmartToxic-7B-private
Dataset Card for Evaluation run of bunnycore/SmartToxic-7B
Dataset automatically created during the evaluation run of model bunnycore/SmartToxic-7B
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-bunnycore-SmartToxic-7B-private.lm-eval-results-vicgalle-CarbonBeagle-11B-truthy-private
Dataset Card for Evaluation run of vicgalle/CarbonBeagle-11B-truthy
Dataset automatically created during the evaluation run of model vicgalle/CarbonBeagle-11B-truthy
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-vicgalle-CarbonBeagle-11B-truthy-private.lm-eval-results-automerger-Inex12Yamshadow-7B-private
Dataset Card for Evaluation run of automerger/Inex12Yamshadow-7B
Dataset automatically created during the evaluation run of model automerger/Inex12Yamshadow-7B
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-automerger-Inex12Yamshadow-7B-private.minimax-m3-deepsearchqa-skill-eval
MiniMax M3 DeepSearchQA Skill Eval
Evaluates minimax/minimax-m3 on google/deepsearchqa using a Pi agent, You.com MCP tools, and a research skill optimized for this harness, model, and tool surface.
MiniMax M3 Medium Reasoning with the You.com research skill reached 74.85% adjusted F1 on DeepSearchQA, above the paper's GPT-5 High Reasoning F1 result. Public artifacts are available for inspection and reproduction.
Links
GitHub:… See the full description on the dataset page: https://huggingface.co/datasets/youdotcom/minimax-m3-deepsearchqa-skill-eval.lm-eval-results-shyamieee-Padma-SLM-7b-v3.0-private
Dataset Card for Evaluation run of shyamieee/Padma-SLM-7b-v3.0
Dataset automatically created during the evaluation run of model shyamieee/Padma-SLM-7b-v3.0
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-shyamieee-Padma-SLM-7b-v3.0-private.sdf_evaluation_traits
Models That Know How Evaluations Are Designed Score Safer
This repository contains the synthetic documents used in the paper Models That Know How Evaluations Are Designed Score Safer.
Project Page | GitHub Repository
Dataset Description
These synthetic documents were used to fine-tune models to investigate evaluation meta-knowledge — parametric knowledge about the structural traits that characterize AI safety evaluations.
Documents were generated using the… See the full description on the dataset page: https://huggingface.co/datasets/compass-group-tue/sdf_evaluation_traits.lm-eval-results-abideen-AlphaMonarch-daser-private
Dataset Card for Evaluation run of abideen/AlphaMonarch-daser
Dataset automatically created during the evaluation run of model abideen/AlphaMonarch-daser
The dataset is composed of 62 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-abideen-AlphaMonarch-daser-private.