Hugging Face's logo

Datasets:
sammshen
/
swebench-minimax-traces-2

Tasks:
Text Generation
Modalities:
Tabular
Text
Formats:
json
Size:
10K - 100K
Tags:
agent-traces
tool-use
multi-turn
benchmark
swebench
Libraries:
Datasets
pandas
Polars
License:
Dataset card Data Studio Files
xet
 Community
1
Dataset Viewer
Auto-converted to Parquet Duplicate
type
string
request_id
string
timestamp_rel_s
float64
timestamp_utc
string
method
string
path
string
query_params
string
headers
string
body
string
task_metadata
string
thread_id
int64
status_code
int64
request
1774734223365708309
34.485094
2026-03-28T21:43:43.365726+00:00
POST
/v1/chat/completions
{}
{"host": "localhost:8206", "accept-encoding": "gzip, deflate, zstd", "connection": "keep-alive", "accept": "application/json", "content-type": "application/json", "user-agent": "OpenAI/Python 2.8.0", "x-stainless-lang": "python", "x-stainless-package-version": "2.8.0", "x-stainless-os": "Linux", "x-stainless-arch": "x6...
{"messages": [{"role": "system", "content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priori...
{"source_dataset": "swebench", "task_id": "django__django-17087", "session_name": "swebench__django__django-17087"}
0
null
response
1774734223365708309
36.068016
2026-03-28T21:43:44.948648+00:00
null
null
null
{"date": "Sat, 28 Mar 2026 21:43:42 GMT", "server": "uvicorn", "content-length": "1150", "content-type": "application/json"}
{"id": "chatcmpl-80b8ceef9e4429d7", "object": "chat.completion", "created": 1774734223, "model": "MiniMaxAI/MiniMax-M2.5", "choices": [{"index": 0, "message": {"role": "assistant", "content": "Let me start by exploring the repository structure to understand the codebase and find the relevant code for this issue.\n\nThe...
{"source_dataset": "swebench", "task_id": "django__django-17087", "session_name": "swebench__django__django-17087"}
0
200
request
1774734225656983257
36.776369
2026-03-28T21:43:45.656997+00:00
POST
/v1/chat/completions
{}
{"host": "localhost:8206", "accept-encoding": "gzip, deflate, zstd", "connection": "keep-alive", "accept": "application/json", "content-type": "application/json", "user-agent": "OpenAI/Python 2.8.0", "x-stainless-lang": "python", "x-stainless-package-version": "2.8.0", "x-stainless-os": "Linux", "x-stainless-arch": "x6...
{"messages": [{"role": "system", "content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priori...
{"source_dataset": "swebench", "task_id": "django__django-17087", "session_name": "swebench__django__django-17087"}
0
null
response
1774734225656983257
37.601099
2026-03-28T21:43:46.481731+00:00
null
null
null
{"date": "Sat, 28 Mar 2026 21:43:44 GMT", "server": "uvicorn", "content-length": "869", "content-type": "application/json"}
{"id": "chatcmpl-94289692af7560f9", "object": "chat.completion", "created": 1774734225, "model": "MiniMaxAI/MiniMax-M2.5", "choices": [{"index": 0, "message": {"role": "assistant", "content": "The workspace is empty. Let me check if there's a django repository somewhere else or if I need to clone it.\n</think>\n\n<func...
{"source_dataset": "swebench", "task_id": "django__django-17087", "session_name": "swebench__django__django-17087"}
0
200
request
1774734228173522085
39.292908
2026-03-28T21:43:48.173540+00:00
POST
/v1/chat/completions
{}
{"host": "localhost:8206", "accept-encoding": "gzip, deflate, zstd", "connection": "keep-alive", "accept": "application/json", "content-type": "application/json", "user-agent": "OpenAI/Python 2.8.0", "x-stainless-lang": "python", "x-stainless-package-version": "2.8.0", "x-stainless-os": "Linux", "x-stainless-arch": "x6...
{"messages": [{"role": "system", "content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priori...
{"source_dataset": "swebench", "task_id": "django__django-17087", "session_name": "swebench__django__django-17087"}
0
null
response
1774734228173522085
40.068313
2026-03-28T21:43:48.948944+00:00
null
null
null
{"date": "Sat, 28 Mar 2026 21:43:47 GMT", "server": "uvicorn", "content-length": "857", "content-type": "application/json"}
{"id": "chatcmpl-98c8e06d0d0c987b", "object": "chat.completion", "created": 1774734228, "model": "MiniMaxAI/MiniMax-M2.5", "choices": [{"index": 0, "message": {"role": "assistant", "content": "The django repository should be in /workspace. Let me check if there's a different location or if I need to clone it.\n</think>...
{"source_dataset": "swebench", "task_id": "django__django-17087", "session_name": "swebench__django__django-17087"}
0
200
request
1774734229638812299
40.758198
2026-03-28T21:43:49.638828+00:00
POST
/v1/chat/completions
{}
"{\"host\": \"localhost:8206\", \"accept-encoding\": \"gzip, deflate, zstd\", \"connection\": \"keep(...TRUNCATED)
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are OpenHands agent, a helpful AI assista(...TRUNCATED)
"{\"source_dataset\": \"swebench\", \"task_id\": \"django__django-17087\", \"session_name\": \"swebe(...TRUNCATED)
0
null
response
1774734229638812299
41.440819
2026-03-28T21:43:50.321451+00:00
null
null
null
"{\"date\": \"Sat, 28 Mar 2026 21:43:48 GMT\", \"server\": \"uvicorn\", \"content-length\": \"806\",(...TRUNCATED)
"{\"id\": \"chatcmpl-b1dbc4b60144d726\", \"object\": \"chat.completion\", \"created\": 1774734229, \(...TRUNCATED)
"{\"source_dataset\": \"swebench\", \"task_id\": \"django__django-17087\", \"session_name\": \"swebe(...TRUNCATED)
0
200
request
1774734231005875431
42.125261
2026-03-28T21:43:51.005892+00:00
POST
/v1/chat/completions
{}
"{\"host\": \"localhost:8206\", \"accept-encoding\": \"gzip, deflate, zstd\", \"connection\": \"keep(...TRUNCATED)
"{\"messages\": [{\"role\": \"system\", \"content\": \"You are OpenHands agent, a helpful AI assista(...TRUNCATED)
"{\"source_dataset\": \"swebench\", \"task_id\": \"django__django-17087\", \"session_name\": \"swebe(...TRUNCATED)
0
null
response
1774734231005875431
43.082653
2026-03-28T21:43:51.963282+00:00
null
null
null
"{\"date\": \"Sat, 28 Mar 2026 21:43:50 GMT\", \"server\": \"uvicorn\", \"content-length\": \"935\",(...TRUNCATED)
"{\"id\": \"chatcmpl-8991aea4e9e93fa6\", \"object\": \"chat.completion\", \"created\": 1774734231, \(...TRUNCATED)
"{\"source_dataset\": \"swebench\", \"task_id\": \"django__django-17087\", \"session_name\": \"swebe(...TRUNCATED)
0
200
End of preview. Expand in Data Studio

swebench-minimax-traces-2

Complete HTTP-level agentic traces from running swebench benchmark tasks through an instrumented reverse proxy.

Each trace captures full request/response pairs including system prompts, user messages, assistant responses, tool calls and results, and token usage metadata.

Stats

  • Total sessions: 250
  • Multi-turn sessions (2+ LLM calls): 210
  • Total records: 15198
  • Total LLM requests: 7623

Format

Raw JSONL traces from the instrumented proxy. Each line is a request or response record:

Request record 

{"type": "request", "request_id": "...", "timestamp_rel_s": 0.0, "timestamp_utc": "...", "method": "POST", "path": "/v1/chat/completions", "headers": {...}, "body": {...}, "thread_id": 0, "task_metadata": {"source_dataset": "swebench", "task_id": "...", "session_name": "..."}}

Response record 

{"type": "response", "request_id": "...", "timestamp_rel_s": 1.23, "timestamp_utc": "...", "status_code": 200, "headers": {...}, "body": {...}, "thread_id": 0, "task_metadata": {"source_dataset": "swebench", "task_id": "...", "session_name": "..."}}

Files

  • swebench_all_traces.jsonl — All sessions merged into one file
  • sessions/ — Individual per-session trace files

Collection Method

Traces collected via instrumented reverse proxy recording all LLM API calls during agent benchmark execution.
Downloads last month
53
Number of rows:
15,198
Total file size:
814 MB