FinanceTasks
Description
FinanceTasks is a synthetic training environment for agentic financial research. Each task is an investor query asked as of a specific date; the agent researches it on the web (SEC filings, earnings call transcripts, press releases, market data) and submits a long-form answer, graded checklist-style against per-query rubrics generated from — and verified against — public primary sources.
Capabilities
- Financial research across the investor workflow: financial data/modeling, sector/industry analysis, earnings/events, company research, coverage/catalyst monitoring, and screening/discovery
- Exhaustive retrieval (temporal across quarters, cross-entity within sectors, thematic within calls)
- Numerical reasoning over financial figures with correct units and periods
- Temporal anchoring: answering relative to the query's as-of date
- Long-form synthesis with professional investor judgement
Compute Requirements
This environment does not require a sandbox; compute requirements are minimal. Grading and web search are API calls.
License
MIT.
Tasks
A single train split with 2,509 tasks (67,904 rubrics; per-task quartiles 16/23/35; 67% must-have). Tasks expose only the query and its as-of date; rubrics stay server-side. Use-case shares track the FrontierFinance eval distribution:
| Use case | FinanceTasks | FrontierFinance |
|---|---|---|
| financial_data_and_modeling | 33.5% | 32% |
| sector_industry_and_macro | 16.3% | 17% |
| earnings_and_events | 11.1% | 16% |
| company_research | 19.0% | 15% |
| coverage_and_catalyst_monitoring | 12.1% | 12% |
| screening_and_discovery | 8.1% | 8% |
Tasks come in five archetypes by document-bundle shape: single_filing (985), cross_entity (633), temporal (547), transcript (220), market (124). Companies referenced in the 220 FrontierFinance eval queries were excluded from the task universe, so training shares no companies with the eval.
Reward Structure
Sparse, LLM-graded reward delivered once when the agent calls submit_answer. Each rubric is an atomic pass/fail criterion; the reward is the query's rubric qualification rate:
$$ R = \frac{\text{rubrics satisfied}}{\text{total rubrics}} \in [0, 1] $$
In test rollouts with gpt-5.2, rewards ranged from 0.08 to 1.00 across tasks (20–47 tool calls per episode), indicating a usable training signal spread rather than saturation.
Tools
web_search— web search (Tavily); returns titles, URLs, and snippetsfetch_url— fetch readable page content (Tavily extract), paginated at ~10,000 characters per pagesubmit_answer— submit the long-form answer for grading; ends the episode
Time Horizon
Multi-turn agentic research episodes ending in a single submission. Test rollouts with gpt-5.2 used 20–47 tool calls depending on query breadth.
Environment Difficulty
Rewards in gpt-5.2 spot-check rollouts spanned 0.08 (a subsidiary-level 10-Q MD&A query) to 1.00 (a single-company quarterly print), with judge fail reasons naming the precise missing figure or comparison. Cross-entity and temporal archetypes generally demand substantially more retrieval than single-filing tasks.
Other Environment Requirements
Two secrets are required:
openai_api_key— for thegpt-5-minigrading judgetavily_api_key— forweb_search/fetch_url
Safety
The agent performs read-only web research on public financial information and produces a text answer; it takes no real-world actions and handles no funds. Standard web-access considerations apply (the agent fetches live third-party content). Answers are research artifacts graded against rubrics, not investment advice, and models trained on this environment should not be treated as licensed financial advisors.
Citations
FinanceTasks is an original synthetic dataset by the General Reasoning team, designed to mirror the task distribution of the FrontierFinance benchmark:
@dataset{GRFinanceTasks,
author = {General Reasoning Inc. Team},
title = {FinanceTasks},
year = {2026},
publisher = {OpenReward},
url = {https://openreward.ai/GeneralReasoning/FinanceTasks}
}