# Open-Domain Question Answering on TQA (test)

Source: [Open-Domain Question Answering on TQA (test)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-tqa-test>)

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

Data updated: 2026-02-26T05:41:36.776Z

Evaluation of Open-Domain Question Answering performance on the test split of the TQA dataset, reporting Exact Match (EM) and F1 scores.

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) | TQA (test) |
| Metric | EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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/open-domain-question-answering-on-tqa-test.md?metric=EM>): Higher is better; unit: PERCENT.

- [F1](<https://www.sota2.com/research/sota/open-domain-question-answering-on-tqa-test.md?metric=F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | EM | Result date | Report paper |
| --- | --- | --- | --- |
| ECoRAG | 66.45 | Not recorded | 68fa792a1e209131cea7c5aa |
| LongLLMLingua | 65.79 | Not recorded | 68fa792a1e209131cea7c5aa |
| ECoRAG | 65.34 | Not recorded | 68fa792a1e209131cea7c5aa |
| BGE-M3 | 65.15 | Not recorded | 68fa792a1e209131cea7c5aa |
| CompAct | 64.37 | Not recorded | 68fa792a1e209131cea7c5aa |
| BGE-M3 | 64.12 | Not recorded | 68fa792a1e209131cea7c5aa |
| RECOMP (extractive) | 62.49 | Not recorded | 68fa792a1e209131cea7c5aa |
| LLMLingua-2 | 53.07 | Not recorded | 68fa792a1e209131cea7c5aa |
| closed-book | 46.48 | Not recorded | 68fa792a1e209131cea7c5aa |
| RECOMP (abstractive) | 43.5 | Not recorded | 68fa792a1e209131cea7c5aa |
| LLMLingua | 42.97 | Not recorded | 68fa792a1e209131cea7c5aa |

### ECoRAG

EM: 66.45. Result ID: 6995cb413badfaffe6cf7892.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Implementation](<https://github.com/ldilab/ECoRAG>)

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":501}. This record does not assert independent reproduction.

### LongLLMLingua

EM: 65.79. Result ID: 6995cb413badfaffe6cf788e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74701e209131cea61c6d.md>)

[Implementation](<https://aka.ms/LLMLingua>)

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":1570}. This record does not assert independent reproduction.

### ECoRAG

EM: 65.34. Result ID: 6995cb413badfaffe6cf78ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Implementation](<https://github.com/ldilab/ECoRAG>)

Recorded evaluation configuration: {"#tokens":441,"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction.

### BGE-M3

EM: 65.15. Result ID: 6995cb413badfaffe6cf78aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d91e209131cea5e7ab.md>)

[Implementation](<https://github.com/FlagOpen/FlagEmbedding>)

Recorded evaluation configuration: {"Top-k retrieval":20,"#tokens":746,"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction.

### CompAct

EM: 64.37. Result ID: 6995cb413badfaffe6cf7891.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75381e209131cea6689e.md>)

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":253}. This record does not assert independent reproduction.

### BGE-M3

EM: 64.12. Result ID: 6995cb413badfaffe6cf78a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d91e209131cea5e7ab.md>)

[Implementation](<https://github.com/FlagOpen/FlagEmbedding>)

Recorded evaluation configuration: {"Top-k retrieval":10,"#tokens":370,"Backbone":"GPT-4o-mini"}. This record does not assert independent reproduction.

### RECOMP (extractive)

EM: 62.49. Result ID: 6995cb413badfaffe6cf788f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

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

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":750}. This record does not assert independent reproduction.

### LLMLingua-2

EM: 53.07. Result ID: 6995cb413badfaffe6cf788d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74701e209131cea61cb2.md>)

[Implementation](<https://aka.ms/LLMLingua-2>)

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":1518}. This record does not assert independent reproduction.

### closed-book

EM: 46.48. Result ID: 6995cb413badfaffe6cf788b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":0}. This record does not assert independent reproduction.

### RECOMP (abstractive)

EM: 43.5. Result ID: 6995cb413badfaffe6cf7890.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

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

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":30}. This record does not assert independent reproduction.

### LLMLingua

EM: 42.97. Result ID: 6995cb413badfaffe6cf788c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792a1e209131cea7c5aa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71621e209131cea5103a.md>)

Recorded evaluation configuration: {"Reader Model":"Flan-UL2","#tokens":726}. This record does not assert independent reproduction.

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