# TAT-QA

TAT-QA is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates numerical question answering over combined tables and prose from financial reports.

## Details

- Address: Online, Global
- Website: [nextplusplus.github.io/TAT-QA/](<https://nextplusplus.github.io/TAT-QA/>)
- Tags: Helpful, Science
- Category: Reasoning
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: exact
- Organization: NExT++
- Released: 2021-05
- Paper: [aclanthology.org/2021.acl-long.254/](<https://aclanthology.org/2021.acl-long.254/>)
- Leaderboard: [nextplusplus.github.io/TAT-QA/](<https://nextplusplus.github.io/TAT-QA/>)
- Repository: [github.com/NExTplusplus/TAT-QA](<https://github.com/NExTplusplus/TAT-QA>)
- Task count: 16,552
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is TAT-QA?

TAT-QA is at Online, Global.

### How do I contact TAT-QA?

To contact TAT-QA, visit https://nextplusplus.github.io/TAT-QA/.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/tat-qa>)
- [Reasoning in Online](<https://aibenchmarkindex.com/global/online/category/reasoning.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.