# Open-domain question answering on Natural Questions (Macro-averaged EM)

Source: [Open-domain question answering on Natural Questions (Macro-averaged EM)](<https://www.sota2.com/research/sota/open-domain-question-answering-on-natural-questions-macro-averaged-em>)

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

Data updated: 2026-02-27T08:17:50.110Z

Evaluation of model performance on the Natural Questions dataset for Open-domain Question Answering, specifically measured using Macro-averaged Exact Match (EM).

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) | Natural Questions |
| Metric | Macro EM |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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

- [Macro EM](<https://www.sota2.com/research/sota/open-domain-question-answering-on-natural-questions-macro-averaged-em.md?metric=Macro%20EM>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro EM | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-3 175B | 11.4 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 13B | 11.2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + T5 3B | 10.8 | Not recorded | 68fa6f7f1e209131cea45f9d |
| NPM | 10.8 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + OPT 6.7B | 10.7 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + OPT 13B | 10.7 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 6.7B | 8.8 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + OPT 2.7B | 8.3 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 175B | 6.4 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + GPT-3 2.7B | 6.1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| BM25 + T5 | 5.2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 13B | 5.2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| OPT 6.7B | 4.2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| OPT 13B | 4.2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 6.7B | 3.1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| OPT 2.7B | 2.1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| T5 3B | 2 | Not recorded | 68fa6f7f1e209131cea45f9d |
| GPT-3 2.7B | 1.1 | Not recorded | 68fa6f7f1e209131cea45f9d |
| T5 | 0.5 | Not recorded | 68fa6f7f1e209131cea45f9d |

### GPT-3 175B

Macro EM: 11.4. Result ID: 69a1531a35dfcabb00e64652.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea261f0.md>)

Recorded evaluation configuration: {"#Params":"500x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 13B

Macro EM: 11.2. Result ID: 69a1531a35dfcabb00e64658.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.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: {"#Params":"37x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + T5 3B

Macro EM: 10.8. Result ID: 69a1531a35dfcabb00e6464b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"8.5x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### NPM

Macro EM: 10.8. Result ID: 69a1531a35dfcabb00e6465a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Implementation](<https://www.sota2.com/github.com/facebookresearch/NPM>)

Recorded evaluation configuration: {"#Params":"1.0x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + OPT 6.7B

Macro EM: 10.7. Result ID: 69a1531a35dfcabb00e64655.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + OPT 13B

Macro EM: 10.7. Result ID: 69a1531a35dfcabb00e64657.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 6.7B

Macro EM: 8.8. Result ID: 69a1531a35dfcabb00e64656.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.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: {"#Params":"19x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + OPT 2.7B

Macro EM: 8.3. Result ID: 69a1531a35dfcabb00e64653.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 175B

Macro EM: 6.4. Result ID: 69a1531a35dfcabb00e64659.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.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: {"#Params":"500x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + GPT-3 2.7B

Macro EM: 6.1. Result ID: 69a1531a35dfcabb00e64654.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.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: {"#Params":"7.6x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### BM25 + T5

Macro EM: 5.2. Result ID: 69a1531a35dfcabb00e6464a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"2.2x","C (Text Corpus)":"true","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 13B

Macro EM: 5.2. Result ID: 69a1531a35dfcabb00e64651.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d6a3.md>)

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### OPT 6.7B

Macro EM: 4.2. Result ID: 69a1531a35dfcabb00e6464e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### OPT 13B

Macro EM: 4.2. Result ID: 69a1531a35dfcabb00e64650.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"#Params":"37x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 6.7B

Macro EM: 3.1. Result ID: 69a1531a35dfcabb00e6464f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e031e209131cea3d6a3.md>)

Recorded evaluation configuration: {"#Params":"19x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### OPT 2.7B

Macro EM: 2.1. Result ID: 69a1531a35dfcabb00e6464c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36474.md>)

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

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### T5 3B

Macro EM: 2. Result ID: 69a1531a35dfcabb00e64649.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"8.5x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### GPT-3 2.7B

Macro EM: 1.1. Result ID: 69a1531a35dfcabb00e6464d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea261f0.md>)

Recorded evaluation configuration: {"#Params":"7.6x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

### T5

Macro EM: 0.5. Result ID: 69a1531a35dfcabb00e64648.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45f9d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c470.md>)

[Implementation](<https://github.com/google-research/text-to-text-transfer-transformer>)

Recorded evaluation configuration: {"#Params":"2.2x","C (Text Corpus)":"false","Zero-shot":"true"}. This record does not assert independent reproduction.

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