zanderjiang/gpt-oss-120b-SWE-Agent
GPT-OSS 120B SWE-Agent Execution Traces Full execution traces of GPT-OSS 120B running SWE-Agent on SWE-Bench (Full). Dataset Structure Each JSON file in traces/ corresponds to one SWE-Bench problem instance. The filename is the instance ID (e.g., django__django-12345.json). Trace Schema { "instance_id": "django__django-12345", "model": "GPT-OSS-120B", "agent": "SWE-agent", "total_steps": 15, "total_run_duration_seconds": 120.5… See the full description on the dataset page: https://huggingface.co/datasets/zanderjiang/gpt-oss-120b-SWE-Agent.
GPT-OSS 120B SWE-Agent Execution Traces
Full execution traces of GPT-OSS 120B running SWE-Agent on SWE-Bench (Full).
Dataset Structure
Each JSON file in traces/ corresponds to one SWE-Bench problem instance. The filename is the instance ID (e.g., django__django-12345.json).
Trace Schema
{
"instance_id": "django__django-12345",
"model": "GPT-OSS-120B",
"agent": "SWE-agent",
"total_steps": 15,
"total_run_duration_seconds": 120.5,
"exit_status": "submitted",
"submission": "<git diff patch>",
"model_stats": { ... },
"steps": [
{
"step_index": 0,
"timestamp": 1711500000.0,
"model_input": [ ... ],
"model_output": {
"raw_response": "full text response from the model",
"thought": "extracted reasoning/thought",
"action": "bash command or tool call",
"thinking_blocks": [],
"tool_calls": [],
"tool_call_ids": []
},
"tool_execution": {
"command": "find /repo -name '*.py' | head -20",
"start_timestamp": 1711500001.0,
"duration_seconds": 0.25,
"output": "file1.py\nfile2.py\n...",
"execution_time_reported": 0.25
},
"exit_status": null,
"done": false,
"submission": null
}
]
}Generation Details
- Model: GPT-OSS 120B served locally via sglang with EAGLE3 speculative decoding (TP=2)
- Agent: SWE-Agent v1.1.0 with thought_action parsing
- Benchmark: SWE-Bench Full