# Open-domain Question Answering on TriviaQA (EM, F1, tokens)

Source: [Open-domain Question Answering on TriviaQA (EM, F1, tokens)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-triviaqa-em-f1-tokens>)

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

Data updated: 2026-04-28T08:10:34.902Z

Evaluation of Open-domain Question Answering performance on the TriviaQA dataset, reporting Exact Match (EM), F1 score, and token count metrics.

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 | Open-domain Question Answering |
| Dataset (including any stated split) | TriviaQA |
| Metric | Exact Match (EM) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Exact Match (EM)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-triviaqa-em-f1-tokens.md?metric=Exact%20Match%20(EM)>): Higher is better; unit: PERCENT.

- [Answer Length (tokens)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-triviaqa-em-f1-tokens.md?metric=Answer%20Length%20(tokens)>): Higher is better; unit: SCALAR.

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

## Recorded results

| Method | Exact Match (EM) | Result date | Report paper |
| --- | --- | --- | --- |
| Oracle | 59.36 | Not recorded | 68fa74aa1e209131cea630b7 |
| Top-5 documents | 48.58 | Not recorded | 68fa74aa1e209131cea630b7 |
| AdaComp | 47.15 | Not recorded | 68fa74aa1e209131cea630b7 |
| ONLY\_DOC | 44.6 | Not recorded | 68fa74aa1e209131cea630b7 |
| Top-1 document | 43.57 | Not recorded | 68fa74aa1e209131cea630b7 |
| RECOMP | 41.77 | Not recorded | 68fa74aa1e209131cea630b7 |
| FILCO | 38.96 | Not recorded | 68fa74aa1e209131cea630b7 |
| LLAMA2-7B | 30.54 | Not recorded | 68fa74aa1e209131cea630b7 |

### Oracle

Exact Match (EM): 59.36. Result ID: 69f06a1647f34ce924d624c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Adaptive Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### Top-5 documents

Exact Match (EM): 48.58. Result ID: 69f06a1647f34ce924d624bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Retrieval without Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### AdaComp

Exact Match (EM): 47.15. Result ID: 69f06a1647f34ce924d624c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Adaptive Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### ONLY\_DOC

Exact Match (EM): 44.6. Result ID: 69f06a1647f34ce924d624c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Retrieval with Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### Top-1 document

Exact Match (EM): 43.57. Result ID: 69f06a1647f34ce924d624be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Retrieval without Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### RECOMP

Exact Match (EM): 41.77. Result ID: 69f06a1647f34ce924d624c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70c81e209131cea4d0a5.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Retrieval with Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### FILCO

Exact Match (EM): 38.96. Result ID: 69f06a1647f34ce924d624c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71301e209131cea4fd9d.md>)

Recorded evaluation configuration: {"Retrieval Strategy":"Retrieval with Compression","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

### LLAMA2-7B

Exact Match (EM): 30.54. Result ID: 69f06a1647f34ce924d624bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74aa1e209131cea630b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eae1e209131cea41685.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Retrieval Strategy":"No Retrieval","Generator":"LLAMA2-7B"}. This record does not assert independent reproduction.

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