datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
swe-bench-lite-agent-traces-v14
AgentBRANE SWE-bench Lite Agent Traces v14
This release contains the 1,890 harness-native agent traces selected by the sealed SWE-bench Lite v14 publication record (1,379/1,890 resolved, 73.0%). It includes Claude Code, Codex, and Pi sessions across seven models and three replicates. No internal research notes are included.
Load the observation table:
from datasets import load_dataset
traces = load_dataset("melissapan/swe-bench-lite-agent-traces-v14", split="train")
Each row… See the full description on the dataset page: https://huggingface.co/datasets/melissapan/swe-bench-lite-agent-traces-v14.swe_doc_gen_SWE-bench_Lite_testSWE-bench_Lite_oracle_easyfrom datasets import load_dataset
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B")
ds = load_dataset("princeton-nlp/SWE-bench_Verified", split="test")
ds_lite = load_dataset("princeton-nlp/SWE-bench_Lite_oracle", split="test")
def count_tokens(text):
return len(tokenizer.encode(text))
ds_easy = ds.filter(lambda x: x["difficulty"] == "<15 min fix")
ds_easy_lite = ds_lite.filter(lambda x: x["instance_id"] in ds_easy["instance_id"])… See the full description on the dataset page: https://huggingface.co/datasets/rasdani/SWE-bench_Lite_oracle_easy.