# Question Answering on TriviaQA (EM, F1, Avg. iter., AUROC)

Source: [Question Answering on TriviaQA (EM, F1, Avg. iter., AUROC)](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-avg-iter-auroc>)

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

Data updated: 2026-06-30T08:19:30.704Z

Evaluation of Question Answering performance on the TriviaQA dataset, reporting Exact Match (EM), F1 score, Average iteration count (Avg. iter.), and Area Under the ROC Curve (AUROC).

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 |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [EM](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-avg-iter-auroc.md?metric=EM>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-avg-iter-auroc.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Average Iterations](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-avg-iter-auroc.md?metric=Average%20Iterations>): Lower is better; unit: SCALAR.

- [AUROC](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-avg-iter-auroc.md?metric=AUROC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| AB-RAG | 40 | Not recorded | 6a434d8dba73165dbb743abe |
| Static RAG | 35.5 | Not recorded | 6a434d8dba73165dbb743abe |

### AB-RAG

EM: 40. Result ID: 6a437bf7fbc373592c946ab6.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d8dba73165dbb743abe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a434d8dba73165dbb743abe.md>)

Recorded evaluation configuration: {"Backbone":"Claude Haiku"}. This record does not assert independent reproduction.

### Static RAG

EM: 35.5. Result ID: 6a437bf7fbc373592c946ab5.

[Reporting paper](<https://www.sota2.com/research/paper/6a434d8dba73165dbb743abe.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: {"Backbone":"Claude Haiku"}. This record does not assert independent reproduction.

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