Datasets:

taiyi-lab
/

apex-agent-eval

Tasks:

Question Answering

Text Generation

Languages:

English

License:

Dataset card Data Studio Files Files and versions

xet

Community

Dataset Preview

Duplicate

Split (1)

train

The full dataset viewer is not available (click to read why). Only showing a preview of the rows.

The dataset generation failed

Error code:   DatasetGenerationError
Exception:    ValueError
Message:      Expected object or value
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1816, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 613, in wrapped
                  for item in generator(*args, **kwargs):
                              ~~~~~~~~~^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 281, in _generate_tables
                  examples = [ujson_loads(line) for line in batch.splitlines()]
                              ~~~~~~~~~~~^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/utils/json.py", line 20, in ujson_loads
                  return pd.io.json.ujson_loads(*args, **kwargs)
                         ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
              ValueError: Expected object or value
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ~~~~~~~~~~~~~~~~~~~~~~~~~^
                      builder, max_dataset_size_bytes=max_dataset_size_bytes
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  )
                  ^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                  ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1683, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ~~~~~~~~~~~~~~~~~~~~~~~~~~^
                      gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  ):
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1869, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

task_id string	task_dir string	run_id string	domain string	task_name string	world_id string	rubric_count int64	score float64	grading_status string	duration_sec null	verifier_count int64	trajectory dict	grades dict	verifiers list	initial_messages list	orchestrator_extra_args dict
task_0097f20dd1744647a5a6e76db215a467	task_0097f20dd1744647a5a6e76db215a467	20260717_174205_250s_c29	Law	World416_JS_02	world_9797d81fa71c4dbfb192e89a0f2ac811	2	0	completed	null	2	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_fd233544","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_93ad092eabf942029f46870b21f187b6","verifier_version":1,"world_id":"world_9797d8(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_00b30f56f39a4a9891d9503443bafb27	task_00b30f56f39a4a9891d9503443bafb27	20260717_174205_250s_c29	Investment Banking	World219_BW_02	world_1e4d4288e63f4a08851a3cc441eb3ccb	5	0.2	completed	null	5	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_80e66e0d","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_81652421c1434b269ec140a4a3d73334","verifier_version":1,"world_id":"world_1e4d42(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_00cd552ee51b4254bae8ee3b0add42fa	task_00cd552ee51b4254bae8ee3b0add42fa	20260717_174205_250s_c29	Investment Banking	World221_oa_2	world_f83f49b3776b4b5e870c36091f7e2b0b	2	0	completed	null	2	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_2605f1cb","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_b0d13e4044334cb791eb3fb0c36d5d2c","verifier_version":1,"world_id":"world_f83f49(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_00db129e3bd9497da0acf6470a1d33d2	task_00db129e3bd9497da0acf6470a1d33d2	20260717_174205_250s_c29	Investment Banking	World228_SM_Task04	world_7cabc3536d2d45f3aa32634046c85921	2	0.5	completed	null	2	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_66423423","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_bfbb63915264470f974510caeaa9c26a","verifier_version":1,"world_id":"world_7cabc3(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_01bf3f1cdf6c432f822f91666047e38c	task_01bf3f1cdf6c432f822f91666047e38c	20260717_174205_250s_c29	Management Consulting	World126_TK_04	world_0f65ffc105a74cc79a207cbe7a2aff87	2	0	completed	null	2	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_000f57f4","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_ea3374d8e60844629e5325252ee5f33c","verifier_version":1,"world_id":"world_0f65ff(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_01ca29fd17b04f43b09cc07d7b1a2ad0	task_01ca29fd17b04f43b09cc07d7b1a2ad0	20260717_174205_250s_c29	Law	World419_UM_04	world_4c8dea260e674f37abc700d5ac09fff9	1	0	completed	null	1	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_e3107d09","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_8376d042fce94a2492b8560458d4bac3","verifier_version":1,"world_id":"world_4c8dea(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_01da0d93b3ad448798d592007d201ef8	task_01da0d93b3ad448798d592007d201ef8	20260717_174205_250s_c29	Investment Banking	World226_TD_05	world_802bca9c604244748d866ba9dde7decf	1	0	completed	null	1	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_aa94e962","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_d4f362d54183410d86949ccbe0f22273","verifier_version":1,"world_id":"world_802bca(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_01fef67b5576468d854319d4d8a84988	task_01fef67b5576468d854319d4d8a84988	20260717_174205_250s_c29	Law	LawWorld417_AS_03	world_e81842899beb4631b2e07feafb4018dd	7	0.857143	completed	null	7	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_bb20d814","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_67d411cb765345348ac62094e4250dea","verifier_version":1,"world_id":"world_e81842(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_0233800d9daf4459bc464ce2f1f822a8	task_0233800d9daf4459bc464ce2f1f822a8	20260717_174205_250s_c29	Management Consulting	Word_129_PJ_01	world_075ef4dff46146a580c8522e2ad29cb3	1	0	error	null	0	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_0c4a2225","grading_run_status":"error","verifier_results":[],"scoring_results"(...TRUNCATED)	[{"verifier_id":"ver_9a300a73b2c941f4b3e1a1b4269d9193","verifier_version":1,"world_id":"world_075ef4(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }
task_052cc6311cf34bc6bacc4f521ba77460	task_052cc6311cf34bc6bacc4f521ba77460	20260717_174205_250s_c29	Investment Banking	World244_SK_Task04	world_43a921f91f0f4d2c85d8bd2774f9e681	1	0	completed	null	1	{"messages":[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning a(...TRUNCATED)	{"grading_run_id":"gr_16692ef2","grading_run_status":"completed","verifier_results":[{"verifier_id":(...TRUNCATED)	[{"verifier_id":"ver_b5815a57d19341d5ae2aca539429a592","verifier_version":1,"world_id":"world_43a921(...TRUNCATED)	[{"role":"system","content":"You are an AI assistant that completes tasks by reasoning and using too(...TRUNCATED)	{ "temperature": 0, "max_tokens": 16384 }

End of preview.

APEX Agents Evaluation Trajectories

This dataset contains the lightweight trajectory artifacts for one full Archipelago / APEX Agents evaluation run.

Run

Run id: 20260717_174205_250s_c29
Benchmark: Mercor Archipelago / APEX Agents
Agent config: react_toolbelt_agent
Max steps: 250
Concurrency: 29
Model: local Qwen3.6-27B-SFT-v10-tau-style-v4-ckpt340 served by SGLang
Tasks: 480

Score Summary

Strict Pass@1: 65 / 480 = 0.1354
Partial average: 0.2822
No-grade counted as zero: 25
Infra failures: 0

Domain Summary

Domain	Tasks	Strict Pass	Strict Pass@1	Partial Avg
Investment Banking	160	18	0.1125	0.1646
Law	160	20	0.1250	0.3582
Management Consulting	160	27	0.1688	0.3237

Files

data/trajectories.jsonl: one JSON object per task, including task metadata, trajectory, grades, verifiers, initial messages, and run score fields.
raw_tasks/<task_id>/: per-task JSON artifacts copied from the evaluator output.
logs/: run manifest, task ids, aggregate results JSONL, and runner log.
summary.json: machine-readable summary.

Large environment snapshots and filesystem archives were intentionally excluded from this upload because the original evaluator output directory is hundreds of GB. This dataset is meant for trajectory inspection and score analysis, not complete environment replay.

Common API key/token patterns were redacted during staging.

Downloads last month: 76

Total file size:

624 MB