alon-albalak/gpt-5-noveltybench-comprehensive-evaluation
收藏Hugging Face2025-12-17 更新2025-12-20 收录
下载链接:
https://hf-mirror.com/datasets/alon-albalak/gpt-5-noveltybench-comprehensive-evaluation
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: completions
list: string
- name: partition
list: int64
- name: distinct
dtype: int64
- name: mean_intra_distance
dtype: float64
- name: std_intra_distance
dtype: float64
- name: min_intra_distance
dtype: float64
- name: max_intra_distance
dtype: float64
- name: num_pairs
dtype: int64
- name: group_size
dtype: int64
- name: reward_scores
list: float64
- name: mean_reward
dtype: float64
- name: std_reward
dtype: float64
- name: min_reward
dtype: float64
- name: max_reward
dtype: float64
- name: judge_responses
list: string
- name: judge_thinking
list: string
- name: judge_scores
list: int64
- name: mean_judge_score
dtype: float64
- name: std_judge_score
dtype: float64
- name: min_judge_score
dtype: float64
- name: max_judge_score
dtype: float64
- name: valid_scores_count
dtype: int64
- name: total_completions
dtype: int64
- name: completion_scores
list: int64
- name: partition_scores
list: int64
- name: utility
dtype: float64
splits:
- name: train
num_bytes: 4352169
num_examples: 100
download_size: 1357212
dataset_size: 4352169
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
提供机构:
alon-albalak



