# Open-domain Question Answering on TriviaQA (Acc, F1, Tok)

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

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

Data updated: 2026-02-27T09:54:44.926Z

Evaluation of Open-domain Question Answering performance on the TriviaQA dataset, reporting Accuracy, F1, and Token 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 | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/open-domain-question-answering-on-triviaqa-acc-f1-tok.md?metric=Accuracy>): Higher is better; unit: PERCENT.

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

- [Token Metric Value](<https://www.sota2.com/research/sota/open-domain-question-answering-on-triviaqa-acc-f1-tok.md?metric=Token%20Metric%20Value>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ChatGPT | 77 | Not recorded | 68fa76311e209131cea6bc1f |
| RetroLLM (Ours) | 74.3 | Not recorded | 68fa76311e209131cea6bc1f |
| Iter-RetGen | 71 | Not recorded | 68fa76311e209131cea6bc1f |
| Naive RAG | 69.3 | Not recorded | 68fa76311e209131cea6bc1f |
| IRCoT | 66 | Not recorded | 68fa76311e209131cea6bc1f |
| REPLUG | 65.4 | Not recorded | 68fa76311e209131cea6bc1f |
| Adaptive-RAG | 65.1 | Not recorded | 68fa76311e209131cea6bc1f |
| Self-RAG | 64.1 | Not recorded | 68fa76311e209131cea6bc1f |
| Mistral-7B | 58.8 | Not recorded | 68fa76311e209131cea6bc1f |
| Llama3-8B | 56.1 | Not recorded | 68fa76311e209131cea6bc1f |
| Qwen2.5-7B | 45.1 | Not recorded | 68fa76311e209131cea6bc1f |

### ChatGPT

Accuracy: 77. Result ID: 69a169d235dfcabb00e6e65c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

Recorded evaluation configuration: {"Generation Type":"Direct Generation"}. This record does not assert independent reproduction.

### RetroLLM (Ours)

Accuracy: 74.3. Result ID: 69a169d235dfcabb00e6e663.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Implementation](<https://github.com/sunnynexus/RetroLLM>)

Recorded evaluation configuration: {"Generation Type":"Retrieval within Generation","Backbone":"Mistral-7B-Instruct"}. This record does not assert independent reproduction.

### Iter-RetGen

Accuracy: 71. Result ID: 69a169d235dfcabb00e6e661.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e48a.md>)

Recorded evaluation configuration: {"Generation Type":"Retrieval-augmented Generation","Retriever":"E5-base-en"}. This record does not assert independent reproduction.

### Naive RAG

Accuracy: 69.3. Result ID: 69a169d235dfcabb00e6e65d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.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: {"Generation Type":"Retrieval-augmented Generation","Retriever":"E5-base-en"}. This record does not assert independent reproduction.

### IRCoT

Accuracy: 66. Result ID: 69a169d235dfcabb00e6e660.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fd81e209131cea4791d.md>)

[Implementation](<https://github.com/stonybrooknlp/ircot>)

Recorded evaluation configuration: {"Generation Type":"Retrieval-augmented Generation","Retriever":"E5-base-en"}. This record does not assert independent reproduction.

### REPLUG

Accuracy: 65.4. Result ID: 69a169d235dfcabb00e6e65e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6b1e209131cea45739.md>)

Recorded evaluation configuration: {"Generation Type":"Retrieval-augmented Generation","Retriever":"E5-base-en"}. This record does not assert independent reproduction.

### Adaptive-RAG

Accuracy: 65.1. Result ID: 69a169d235dfcabb00e6e662.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c66.md>)

Recorded evaluation configuration: {"Generation Type":"Retrieval-augmented Generation","Retriever":"E5-base-en"}. This record does not assert independent reproduction.

### Self-RAG

Accuracy: 64.1. Result ID: 69a169d235dfcabb00e6e65f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e51e209131cea4dc1c.md>)

[Implementation](<https://selfrag.github.io/>)

Recorded evaluation configuration: {"Generation Type":"Retrieval-augmented Generation","Retriever":"E5-base-en"}. This record does not assert independent reproduction.

### Mistral-7B

Accuracy: 58.8. Result ID: 69a169d235dfcabb00e6e65a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Generation Type":"Direct Generation"}. This record does not assert independent reproduction.

### Llama3-8B

Accuracy: 56.1. Result ID: 69a169d235dfcabb00e6e659.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Generation Type":"Direct Generation"}. This record does not assert independent reproduction.

### Qwen2.5-7B

Accuracy: 45.1. Result ID: 69a169d235dfcabb00e6e65b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76311e209131cea6bc1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74bf1e209131cea6378d.md>)

[Implementation](<https://github.com/QwenLM/Qwen2>)

Recorded evaluation configuration: {"Generation Type":"Direct Generation"}. This record does not assert independent reproduction.

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