# Open-QA Evaluation on EVOUNA-NaturalQuestions

Source: [Open-QA Evaluation on EVOUNA-NaturalQuestions](<https://www.sota2.com/research/sota/open-qa-evaluation-on-evouna-naturalquestions>)

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

Data updated: 2026-02-26T05:43:20.539Z

Evaluation of model performance on the EVOUNA-NaturalQuestions dataset for Open Question Answering, measured using F1 score and 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 | Open-QA Evaluation |
| Dataset (including any stated split) | EVOUNA-NaturalQuestions |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 35 of 35 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/open-qa-evaluation-on-evouna-naturalquestions.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/open-qa-evaluation-on-evouna-naturalquestions.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Another Human | 97.9 | Not recorded | 68fa734d1e209131cea5baa2 |
| Another Human | 97.8 | Not recorded | 68fa734d1e209131cea5baa2 |
| Another Human | 97.4 | Not recorded | 68fa734d1e209131cea5baa2 |
| Another Human | 97.2 | Not recorded | 68fa734d1e209131cea5baa2 |
| Another Human | 96.5 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 (best prompting) | 95.5 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 | 95.3 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment | 94.8 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment | 93.8 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment | 92.7 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment | 92.6 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment | 92.6 | Not recorded | 68fa734d1e209131cea5baa2 |
| Lexical Match | 92 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment (small) | 91.5 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 (best prompting) | 91.2 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment (small) | 89.9 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 (best prompting) | 89.4 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 (best prompting) | 88.3 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment (small) | 88 | Not recorded | 68fa734d1e209131cea5baa2 |
| Lexical Match | 87.8 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment (small) | 87.8 | Not recorded | 68fa734d1e209131cea5baa2 |
| Entailment (small) | 87.7 | Not recorded | 68fa734d1e209131cea5baa2 |
| Lexical Match | 87.6 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 | 87.2 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 (best prompting) | 87.1 | Not recorded | 68fa734d1e209131cea5baa2 |
| Lexical Match | 86.9 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 | 86.9 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 | 86.8 | Not recorded | 68fa734d1e209131cea5baa2 |
| Lexical Match | 85 | Not recorded | 68fa734d1e209131cea5baa2 |
| BERTScore | 84.3 | Not recorded | 68fa734d1e209131cea5baa2 |
| BERTScore | 83.5 | Not recorded | 68fa734d1e209131cea5baa2 |
| BERTScore | 81.2 | Not recorded | 68fa734d1e209131cea5baa2 |
| BERTScore | 77.6 | Not recorded | 68fa734d1e209131cea5baa2 |
| BERTScore | 77.5 | Not recorded | 68fa734d1e209131cea5baa2 |
| GPT-3.5 | 77.3 | Not recorded | 68fa734d1e209131cea5baa2 |

### Another Human

F1 Score: 97.9. Result ID: 6992d1203a6c31484911b24e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### Another Human

F1 Score: 97.8. Result ID: 6992d1203a6c31484911b24c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### Another Human

F1 Score: 97.4. Result ID: 6992d1203a6c31484911b24b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### Another Human

F1 Score: 97.2. Result ID: 6992d1203a6c31484911b24f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

### Another Human

F1 Score: 96.5. Result ID: 6992d1203a6c31484911b24d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### GPT-3.5 (best prompting)

F1 Score: 95.5. Result ID: 6992d1203a6c31484911b246.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ff81e209131cea483c9.md>)

[Implementation](<https://github.com/ehsk/OpenQA-eval>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### GPT-3.5

F1 Score: 95.3. Result ID: 6992d1203a6c31484911b237.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### Entailment

F1 Score: 94.8. Result ID: 6992d1203a6c31484911b23c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### Entailment

F1 Score: 93.8. Result ID: 6992d1203a6c31484911b23f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### Entailment

F1 Score: 92.7. Result ID: 6992d1203a6c31484911b23d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### Entailment

F1 Score: 92.6. Result ID: 6992d1203a6c31484911b23e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### Entailment

F1 Score: 92.6. Result ID: 6992d1203a6c31484911b240.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

### Lexical Match

F1 Score: 92. Result ID: 6992d1203a6c31484911b22d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### Entailment (small)

F1 Score: 91.5. Result ID: 6992d1203a6c31484911b241.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### GPT-3.5 (best prompting)

F1 Score: 91.2. Result ID: 6992d1203a6c31484911b249.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ff81e209131cea483c9.md>)

[Implementation](<https://github.com/ehsk/OpenQA-eval>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### Entailment (small)

F1 Score: 89.9. Result ID: 6992d1203a6c31484911b244.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### GPT-3.5 (best prompting)

F1 Score: 89.4. Result ID: 6992d1203a6c31484911b248.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ff81e209131cea483c9.md>)

[Implementation](<https://github.com/ehsk/OpenQA-eval>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### GPT-3.5 (best prompting)

F1 Score: 88.3. Result ID: 6992d1203a6c31484911b247.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ff81e209131cea483c9.md>)

[Implementation](<https://github.com/ehsk/OpenQA-eval>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### Entailment (small)

F1 Score: 88. Result ID: 6992d1203a6c31484911b242.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### Lexical Match

F1 Score: 87.8. Result ID: 6992d1203a6c31484911b231.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

### Entailment (small)

F1 Score: 87.8. Result ID: 6992d1203a6c31484911b245.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

### Entailment (small)

F1 Score: 87.7. Result ID: 6992d1203a6c31484911b243.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Implementation](<https://github.com/U-Alberta/QA-partial-marks>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### Lexical Match

F1 Score: 87.6. Result ID: 6992d1203a6c31484911b230.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### GPT-3.5

F1 Score: 87.2. Result ID: 6992d1203a6c31484911b238.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### GPT-3.5 (best prompting)

F1 Score: 87.1. Result ID: 6992d1203a6c31484911b24a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ff81e209131cea483c9.md>)

[Implementation](<https://github.com/ehsk/OpenQA-eval>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

### Lexical Match

F1 Score: 86.9. Result ID: 6992d1203a6c31484911b22e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### GPT-3.5

F1 Score: 86.9. Result ID: 6992d1203a6c31484911b239.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### GPT-3.5

F1 Score: 86.8. Result ID: 6992d1203a6c31484911b23a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### Lexical Match

F1 Score: 85. Result ID: 6992d1203a6c31484911b22f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### BERTScore

F1 Score: 84.3. Result ID: 6992d1203a6c31484911b235.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"GPT-4"}. This record does not assert independent reproduction.

### BERTScore

F1 Score: 83.5. Result ID: 6992d1203a6c31484911b232.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"DPR-FiD"}. This record does not assert independent reproduction.

### BERTScore

F1 Score: 81.2. Result ID: 6992d1203a6c31484911b234.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"ChatGPT"}. This record does not assert independent reproduction.

### BERTScore

F1 Score: 77.6. Result ID: 6992d1203a6c31484911b233.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"InstructGPT"}. This record does not assert independent reproduction.

### BERTScore

F1 Score: 77.5. Result ID: 6992d1203a6c31484911b236.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

### GPT-3.5

F1 Score: 77.3. Result ID: 6992d1203a6c31484911b23b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa734d1e209131cea5baa2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e458.md>)

[Implementation](<https://github.com/wangcunxiang/QA-Eval>)

Recorded evaluation configuration: {"QA System":"BingChat"}. This record does not assert independent reproduction.

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