# Question Answering on TriviaQA wiki split (test)

Source: [Question Answering on TriviaQA wiki split (test)](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-wiki-split-test>)

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

Data updated: 2026-02-26T05:27:40.752Z

Evaluation of Question Answering performance on the test split of the TriviaQA dataset, specifically using the Wiki domain subset, reporting Accuracy.

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 | Question Answering |
| Dataset (including any stated split) | TriviaQA wiki split (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-wiki-split-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-3 | 71.2 | Not recorded | 68fa680c1e209131cea19d53 |
| RAG | 68 | Not recorded | 68fa680c1e209131cea19d53 |
| GPT-3 | 68 | Not recorded | 68fa680c1e209131cea19d53 |
| GPT-3 | 64.3 | Not recorded | 68fa680c1e209131cea19d53 |
| T5-11B+SSM | 60.5 | Not recorded | 68fa680c1e209131cea19d53 |
| T5-11B | 50.1 | Not recorded | 68fa680c1e209131cea19d53 |

### GPT-3

Accuracy: 71.2. Result ID: 698d57ce8b517eb43320c5b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Learning Protocol":"Few-Shot","QA Environment":"Closed-Book"}. This record does not assert independent reproduction.

### RAG

Accuracy: 68. Result ID: 698d57ce8b517eb43320c5b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b91e209131cea23c26.md>)

[Implementation](<https://github.com/huggingface/transformers/blob/master/examples/rag/>)

Recorded evaluation configuration: {"Setting":"Fine-tuned","QA Environment":"Open-Domain"}. This record does not assert independent reproduction.

### GPT-3

Accuracy: 68. Result ID: 698d57ce8b517eb43320c5b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Learning Protocol":"One-Shot","QA Environment":"Closed-Book"}. This record does not assert independent reproduction.

### GPT-3

Accuracy: 64.3. Result ID: 698d57ce8b517eb43320c5b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

Recorded evaluation configuration: {"Learning Protocol":"Zero-Shot","QA Environment":"Closed-Book"}. This record does not assert independent reproduction.

### T5-11B+SSM

Accuracy: 60.5. Result ID: 698d57ce8b517eb43320c5b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686b1e209131cea1bfe3.md>)

Recorded evaluation configuration: {"Setting":"Fine-tuned","QA Environment":"Closed-Book","Auxiliary Training":"SSM"}. This record does not assert independent reproduction.

### T5-11B

Accuracy: 50.1. Result ID: 698d57ce8b517eb43320c5b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686b1e209131cea1bfe3.md>)

Recorded evaluation configuration: {"Setting":"Fine-tuned","QA Environment":"Closed-Book"}. This record does not assert independent reproduction.

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