# Complex Factual Reasoning on BBH

Source: [Complex Factual Reasoning on BBH](<https://www.sota2.com/research/sota/complex-factual-reasoning-on-bbh>)

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

Data updated: 2026-05-19T12:05:36.875Z

Evaluation of model performance on complex factual reasoning tasks using the Big-Bench Hard (BBH) benchmark, reporting a general Score.

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 | Complex Factual Reasoning |
| Dataset (including any stated split) | BBH |
| Metric | BBH Complex Factual Reasoning Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [BBH Complex Factual Reasoning Score](<https://www.sota2.com/research/sota/complex-factual-reasoning-on-bbh.md?metric=BBH%20Complex%20Factual%20Reasoning%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BBH Complex Factual Reasoning Score | Result date | Report paper |
| --- | --- | --- | --- |
| FedSDR | 35.81 | Not recorded | 6a0beecfdbc836b87d82c6fd |
| FedSD | 34.86 | Not recorded | 6a0beecfdbc836b87d82c6fd |
| Dual-LoRA(FedDPA) | 34.23 | Not recorded | 6a0beecfdbc836b87d82c6fd |
| Baseline(FedAvg) | 34.21 | Not recorded | 6a0beecfdbc836b87d82c6fd |
| Dual Upload | 31.89 | Not recorded | 6a0beecfdbc836b87d82c6fd |
| Distill Rect | 30.79 | Not recorded | 6a0beecfdbc836b87d82c6fd |

### FedSDR

BBH Complex Factual Reasoning Score: 35.81. Result ID: 6a0c520bfbc373592c039e88.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

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

### FedSD

BBH Complex Factual Reasoning Score: 34.86. Result ID: 6a0c520bfbc373592c039e87.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

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

### Dual-LoRA(FedDPA)

BBH Complex Factual Reasoning Score: 34.23. Result ID: 6a0c520bfbc373592c039e86.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75fe1e209131cea6acc4.md>)

[Implementation](<https://github.com/Lydia-yang/FedDPA>)

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

### Baseline(FedAvg)

BBH Complex Factual Reasoning Score: 34.21. Result ID: 6a0c520bfbc373592c039e83.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

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

### Dual Upload

BBH Complex Factual Reasoning Score: 31.89. Result ID: 6a0c520bfbc373592c039e85.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

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

### Distill Rect

BBH Complex Factual Reasoning Score: 30.79. Result ID: 6a0c520bfbc373592c039e84.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beecfdbc836b87d82c6fd.md>)

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

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