{"taskset": {"n_runnable": 0, "name": "Finance Agent Benchmark", "url_data": "https://huggingface.co/datasets/vals-ai/finance_agent_benchmark", "catalog_id": "vals-finance-agent", "owner_type": "company", "cited_by": ["Gemini 3.8 Flash", "Kimi K3", "Nemotron 3 Ultra"], "taskset": "financeagent", "domain": "finance", "task_kind": "financial research on SEC filings with tools", "environment": "live-web", "grading": "llm-judge", "path": "datasets/financeagent", "n_single_container": 50, "n_tasks": 50, "domain_raw": "finance", "sample_instruction": "How has US Steel addressed its planned merger with Nippon Steel and its effect on its business operations?", "owner_org": "Vals AI", "url_repo": "https://github.com/vals-ai/finance-agent", "url_paper": "https://arxiv.org/abs/2508.00828", "license": "CC-BY-4.0", "languages": [], "difficulties": {"?": 50}, "categories": ["financeQA"]}, "tasks": [{"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-0", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-1", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-10", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-11", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-12", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-13", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-14", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-15", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-16", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-17", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-18", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-19", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-2", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-20", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-21", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-22", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-23", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-24", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-25", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-26", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-27", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-28", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-29", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-3", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-30", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-31", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-32", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-33", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-34", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-35", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-36", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-37", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-38", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-39", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-4", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-40", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-41", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-42", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-43", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-44", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-45", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-46", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-47", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-48", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-49", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-5", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-6", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-7", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-8", "taskset": "financeagent"}, {"agent_timeout": 3600, "category": "financeQA", "compose": false, "difficulty": "", "language": "", "oracle": null, "runnable": false, "tags": ["finance"], "task": "financeagent-9", "taskset": "financeagent"}], "next": null}