Dataset Preview
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: TypeError
Message: Couldn't cast array of type int64 to null
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1816, in _prepare_split_single
for key, table in generator:
^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 310, in _generate_tables
self._cast_table(pa_table, json_field_paths=json_field_paths),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/packaged_modules/json/json.py", line 130, in _cast_table
pa_table = table_cast(pa_table, self.info.features.arrow_schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2369, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2303, in cast_table_to_schema
cast_array_to_feature(
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1852, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2059, in cast_array_to_feature
_c(array.field(name) if name in array_fields else null_array, subfeature)
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1854, in wrapper
return func(array, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2143, in cast_array_to_feature
return array_cast(
^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1854, in wrapper
return func(array, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2005, in array_cast
raise TypeError(f"Couldn't cast array of type {_short_str(array.type)} to {_short_str(pa_type)}")
TypeError: Couldn't cast array of type int64 to null
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 1348, in compute_config_parquet_and_info_response
parquet_operations = convert_to_parquet(builder)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 980, in convert_to_parquet
builder.download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 890, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 951, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1683, in _prepare_split
for job_id, done, content in self._prepare_split_single(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/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 datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
model_path string | user_model_path string | benchmark_name string | task_name string | sampling_params dict | user_sampling_params dict | messages list | eval_result dict | meta dict |
|---|---|---|---|---|---|---|---|---|
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [
{
"role": "system",
"content": "# Retail agent policy\n\nAs a retail agent, you can help users cancel or modify pending orders, return or exchange delivered orders, modify their default user address, or provide information about their own profile, orders, and related products.\n\n- At the beginning of the c... | {
"score": 1,
"db_match": true
} | {
"id": "retail_0",
"is_correct": true,
"finish_reason": "user_stop",
"run_timestamp": null,
"simulation_start_time": null,
"simulation_end_time": null,
"duration_seconds": null,
"agent_cost": 0,
"user_cost": 0.0007,
"reward_details": {
"db_reward": 1,
"reward_breakdown": null,
"nl_asser... |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [
{
"role": "system",
"content": "# Retail agent policy\n\nAs a retail agent, you can help users cancel or modify pending orders, return or exchange delivered orders, modify their default user address, or provide information about their own profile, orders, and related products.\n\n- At the beginning of the c... | {
"score": 1,
"db_match": true
} | {
"id": "retail_1",
"is_correct": true,
"finish_reason": "user_stop",
"run_timestamp": null,
"simulation_start_time": null,
"simulation_end_time": null,
"duration_seconds": null,
"agent_cost": 0,
"user_cost": 0.0008,
"reward_details": {
"db_reward": 1,
"reward_breakdown": null,
"nl_asser... |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [
{
"role": "system",
"content": "# Retail agent policy\n\nAs a retail agent, you can help users cancel or modify pending orders, return or exchange delivered orders, modify their default user address, or provide information about their own profile, orders, and related products.\n\n- At the beginning of the c... | {
"score": 1,
"db_match": false
} | {
"id": "retail_2",
"is_correct": false,
"finish_reason": "user_stop",
"run_timestamp": null,
"simulation_start_time": null,
"simulation_end_time": null,
"duration_seconds": null,
"agent_cost": 0,
"user_cost": 0.0008,
"reward_details": {
"db_reward": null,
"reward_breakdown": null,
"nl_a... |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [
{
"role": "system",
"content": "# Retail agent policy\n\nAs a retail agent, you can help users cancel or modify pending orders, return or exchange delivered orders, modify their default user address, or provide information about their own profile, orders, and related products.\n\n- At the beginning of the c... | {
"score": 0,
"db_match": false
} | {
"id": "retail_3",
"is_correct": false,
"finish_reason": "user_stop",
"run_timestamp": null,
"simulation_start_time": null,
"simulation_end_time": null,
"duration_seconds": null,
"agent_cost": 0,
"user_cost": 0.0008,
"reward_details": {
"db_reward": null,
"reward_breakdown": null,
"nl_a... |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [
{
"role": "system",
"content": "# Retail agent policy\n\nAs a retail agent, you can help users cancel or modify pending orders, return or exchange delivered orders, modify their default user address, or provide information about their own profile, orders, and related products.\n\n- At the beginning of the c... | {
"score": 0,
"db_match": false
} | {
"id": "retail_4",
"is_correct": false,
"finish_reason": "user_stop",
"run_timestamp": null,
"simulation_start_time": null,
"simulation_end_time": null,
"duration_seconds": null,
"agent_cost": 0,
"user_cost": 0.0007,
"reward_details": {
"db_reward": null,
"reward_breakdown": null,
"nl_a... |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [
{
"role": "system",
"content": "# Retail agent policy\n\nAs a retail agent, you can help users cancel or modify pending orders, return or exchange delivered orders, modify their default user address, or provide information about their own profile, orders, and related products.\n\n- At the beginning of the c... | {
"score": 1,
"db_match": true
} | {
"id": "retail_5",
"is_correct": true,
"finish_reason": "user_stop",
"run_timestamp": null,
"simulation_start_time": null,
"simulation_end_time": null,
"duration_seconds": null,
"agent_cost": 0,
"user_cost": 0.001,
"reward_details": {
"db_reward": 1,
"reward_breakdown": null,
"nl_assert... |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [{"role":"system","content":"# Retail agent policy\n\nAs a retail agent, you can help users cancel o(...TRUNCATED) | {
"score": 1,
"db_match": true
} | {"id":"retail_6","is_correct":true,"finish_reason":"user_stop","run_timestamp":null,"simulation_star(...TRUNCATED) |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [{"role":"system","content":"# Retail agent policy\n\nAs a retail agent, you can help users cancel o(...TRUNCATED) | {
"score": 1,
"db_match": true
} | {"id":"retail_7","is_correct":true,"finish_reason":"user_stop","run_timestamp":null,"simulation_star(...TRUNCATED) |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [{"role":"system","content":"# Retail agent policy\n\nAs a retail agent, you can help users cancel o(...TRUNCATED) | {
"score": 1,
"db_match": true
} | {"id":"retail_8","is_correct":true,"finish_reason":"user_stop","run_timestamp":null,"simulation_star(...TRUNCATED) |
deepseek-ai/DeepSeek-R1-0528 | openai/gpt-4o-20240806 | taubench | retail | {
"max_tokens": null,
"temperature": 0
} | {
"temperature": null
} | [{"role":"system","content":"# Retail agent policy\n\nAs a retail agent, you can help users cancel o(...TRUNCATED) | {
"score": 1,
"db_match": true
} | {"id":"retail_9","is_correct":true,"finish_reason":"user_stop","run_timestamp":null,"simulation_star(...TRUNCATED) |
End of preview.
AgentSuite/tau-bench-trajectories
Per-model agent trajectory data for tau-bench (public release).
- Models: 30
- Tasks per model: 165
- One file per model:
{model}.jsonl, one JSON object per line. - Fields:
model_path,user_model_path,benchmark_name,task_name,sampling_params,user_sampling_params,messages,eval_result,meta. sampling_paramsreflect each benchmark's own implementation; values the benchmark leaves unset are recorded asnull(provider default).
Models
DeepSeek-R1-0528DeepSeek-V3-0324DeepSeek-V3.2-Exp-thinking-offDeepSeek-V3.2-Exp-thinking-onKimi-K2-InstructKimi-K2-Instruct-0905Qwen3-235B-A22B-FP8Qwen3-235B-A22B-Instruct-2507-FP8Qwen3-235B-A22B-Thinking-2507-FP8Qwen3-Coder-480B-A35B-Instruct-FP8claude-4-opus-thinking-offclaude-4-opus-thinking-on-10kclaude-4-sonnet-thinking-offclaude-4-sonnet-thinking-on-10kclaude-4.5-sonnet-thinking-offclaude-4.5-sonnet-thinking-on-10kgemini-2.5-flash-thinking-offgemini-2.5-flash-thinking-ongemini-2.5-pro-thinking-ongpt-4.1gpt-4.1-minigpt-4.1-nanogpt-4o-20240806gpt-4o-minigpt-5gpt-5-nanogpt-oss-120bgpt-oss-20bo3-higho4-mini-high
- Downloads last month
- -