1024m/PHI-4-Hindi-Instruct-Data dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset Card for Evaluation run of microsoft/phi-4

Dataset automatically created during the evaluation run of model microsoft/phi-4. The dataset is composed of 116 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 1 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 configuration… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_microsoft_phi-4_v2.

Raw responses generated by Phi4 , questions from alamios/Mistral-Small-24B-Instruct-2501-Conversations Made it to use on the QwenPhi 0.5B Draft model, but the finetune did not yield much improvement, still I have generated the dataset so here is the raw data hopefully it is useful for someone.

Dataset Card for Evaluation run of microsoft/Phi-4-mini-instruct

Dataset automatically created during the evaluation run of model microsoft/Phi-4-mini-instruct. The dataset is composed of 1 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 1 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/OALL/details_microsoft_Phi-4-mini-instruct_v2_alrage.

R0bfried/RAGAS-BASE-phi-4-eval2 dataset hosted on Hugging Face and contributed by the HF Datasets community

mlfoundations-dev/Phi-4-reasoning-plus_eval_2693 dataset hosted on Hugging Face and contributed by the HF Datasets community

Malthe/phi4-hallucination-embeddings dataset hosted on Hugging Face and contributed by the HF Datasets community

ykarout/code-reasoning-phi4-template dataset hosted on Hugging Face and contributed by the HF Datasets community

FineTome-Phi4-Format

This dataset contains 15000 samples from the mlabonne/FineTome-100k dataset, formatted specifically for Phi-4 models with the system prompt set to "detailed thinking off".

  Format

Each example follows the Phi chat format: <|im_start|>system<|im_sep|>detailed thinking off<|im_end|> <|im_start|>user<|im_sep|>[User content]<|im_end|> <|im_start|>assistant<|im_sep|>[Assistant response]<|im_end|>

  Source

The original data comes from… See the full description on the dataset page: https://huggingface.co/datasets/ykarout/finetome-phi4-format.

alex-miller/crs-2014-2023-housing-labeled-phi4 dataset hosted on Hugging Face and contributed by the HF Datasets community

ykarout/nemotron-phi4-format-data dataset hosted on Hugging Face and contributed by the HF Datasets community

Nemotron Phi-4 Format Dataset

This dataset contains examples extracted from NVIDIA/Llama-Nemotron-Post-Training-Dataset, filtered and formatted for Phi-4 fine-tuning.

  Dataset Details

Source: NVIDIA/Llama-Nemotron-Post-Training-Dataset Splits: code, math, science Filter: system_prompt="detailed thinking on", output length between 8000-10000 characters Format: Phi-4 chat template Size: 20000 examples

  Format

Examples follow the Phi-4 chat template:… See the full description on the dataset page: https://huggingface.co/datasets/ykarout/nvidia-nemotron-sampled-phi4-format.

Phi-4 Math Chat Dataset (10k)

This dataset contains 10,000 carefully selected math reasoning samples formatted using the Phi-4 chat template. Each entry consists of:

A user message: the math question An assistant message: a final concise answer, extracted from deeper reasoning chains

  Format

Each example follows the Phi-4 chat format: <|im_start|>user<|im_sep|>question<|im_end|> <|im_start|>assistant<|im_sep|>answer<|im_end|>

  Usage

This dataset is suitable… See the full description on the dataset page: https://huggingface.co/datasets/ykarout/phi4-math-chat-10k.

GhulamShabbirKhan/BankFAQs-Phi4 dataset hosted on Hugging Face and contributed by the HF Datasets community

gx-ai-architect/numinamath-178k-phi4-bon-verified-dpo-trl-40k-old-r1-format dataset hosted on Hugging Face and contributed by the HF Datasets community

R0bfried/RAGAS-INSTRUCT-phi-4-eval2 dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset Card for Evaluation run of FINGU-AI/Phi-4-RRStock

Dataset automatically created during the evaluation run of model FINGU-AI/Phi-4-RRStock The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task. The dataset has been created from 1 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/open-llm-leaderboard/FINGU-AI_Phi-4-RRStock-details.

kadirnar/Emilia-All-Ja-Phi-4-mini-instruct dataset hosted on Hugging Face and contributed by the HF Datasets community

mlfoundations-dev/Phi-4-reasoning-plus_eval_5554

Precomputed model outputs for evaluation.

  Evaluation Results





  Summary

Metric AIME24 AMC23 MATH500 MMLUPro JEEBench GPQADiamond LiveCodeBench CodeElo CodeForces HLE HMMT AIME25 LiveCodeBenchv5

Accuracy 76.0 96.2 84.0 14.6 83.5 66.8 0.8 2.4 3.5 7.1 53.0 68.0 0.5

  AIME24

Average Accuracy: 76.00% ± 1.23% Number of Runs: 10

Run Accuracy Questions Solved Total Questions

1… See the full description on the dataset page: https://huggingface.co/datasets/mlfoundations-dev/Phi-4-reasoning-plus_eval_5554.

Dataset Card for Evaluation run of bunnycore/Phi-4-Model-Stock-v4

Dataset automatically created during the evaluation run of model bunnycore/Phi-4-Model-Stock-v4 The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task. The dataset has been created from 1 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.… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/bunnycore_Phi-4-Model-Stock-v4-details.