# Time Series Question Answering on MTBench

Source: [Time Series Question Answering on MTBench](<https://www.sota2.com/research/sota/time-series-question-answering-on-mtbench>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:45:18.864Z

Evaluation of Time Series Question Answering capabilities using specific subsets of the MTBench dataset, including FinanceQA and WeatherQA across different time horizons (7-Day, 14-Day, 30-Day).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Time Series Question Answering |
| Dataset (including any stated split) | MTBench |
| Metric | FinanceQA (7D) Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [FinanceQA (7D) Acc](<https://www.sota2.com/research/sota/time-series-question-answering-on-mtbench.md?metric=FinanceQA%20(7D)%20Acc>): Higher is better; unit: PERCENT.

- [WeatherQA (7D) Acc](<https://www.sota2.com/research/sota/time-series-question-answering-on-mtbench.md?metric=WeatherQA%20(7D)%20Acc>): Higher is better; unit: PERCENT.

- [FinanceQA (30D) Acc](<https://www.sota2.com/research/sota/time-series-question-answering-on-mtbench.md?metric=FinanceQA%20(30D)%20Acc>): Higher is better; unit: PERCENT.

- [WeatherQA (14D) Acc](<https://www.sota2.com/research/sota/time-series-question-answering-on-mtbench.md?metric=WeatherQA%20(14D)%20Acc>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/time-series-question-answering-on-mtbench.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FinanceQA (7D) Acc | Result date | Report paper |
| --- | --- | --- | --- |
| TIMEOMNI-1 | 72.1 | Not recorded | 68fa7bc71e209131cea8a6ba |
| GPT-4o | 65.1 | Not recorded | 68fa7bc71e209131cea8a6ba |
| Qwen2.5-Instruct-7B | 62.2 | Not recorded | 68fa7bc71e209131cea8a6ba |

### TIMEOMNI-1

FinanceQA (7D) Acc: 72.1. Result ID: 699ae5075698665ec4752cca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6ba.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-4o

FinanceQA (7D) Acc: 65.1. Result ID: 699ae5075698665ec4752cc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77951e209131cea7425a.md>)

Recorded evaluation configuration: {"Source":"Original Paper"}. This record does not assert independent reproduction.

### Qwen2.5-Instruct-7B

FinanceQA (7D) Acc: 62.2. Result ID: 699ae5075698665ec4752cc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc71e209131cea8a6ba.md>)

Recorded evaluation configuration: {"Type":"Base Model"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.