# Question Answering on NQ, TriviaQA, BioASQ, and PopQA

Source: [Question Answering on NQ, TriviaQA, BioASQ, and PopQA](<https://www.sota2.com/research/sota/question-answering-on-nq-triviaqa-bioasq-and-popqa>)

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

Data updated: 2026-02-26T05:30:35.196Z

Evaluation of Question Answering performance aggregated across the NQ, TriviaQA, BioASQ, and PopQA datasets.

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 | Question Answering |
| Dataset (including any stated split) | Overall NQ, TriviaQA, BioASQ, PopQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 32 of 32 |
| 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/question-answering-on-nq-triviaqa-bioasq-and-popqa.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ASTUTE RAG | 0.617 | Not recorded | 68fa79061e209131cea7bc2c |
| ASTUTE RAG | 0.599 | Not recorded | 68fa79061e209131cea7bc2c |
| USC | 0.595 | Not recorded | 68fa79061e209131cea7bc2c |
| ASTUTE RAG | 0.592 | Not recorded | 68fa79061e209131cea7bc2c |
| InstructRAG | 0.588 | Not recorded | 68fa79061e209131cea7bc2c |
| USC | 0.587 | Not recorded | 68fa79061e209131cea7bc2c |
| Self-Route | 0.581 | Not recorded | 68fa79061e209131cea7bc2c |
| Self-Route | 0.576 | Not recorded | 68fa79061e209131cea7bc2c |
| InstructRAG | 0.567 | Not recorded | 68fa79061e209131cea7bc2c |
| RobustRAG | 0.565 | Not recorded | 68fa79061e209131cea7bc2c |
| USC | 0.564 | Not recorded | 68fa79061e209131cea7bc2c |
| Self-Route | 0.562 | Not recorded | 68fa79061e209131cea7bc2c |
| InstructRAG | 0.561 | Not recorded | 68fa79061e209131cea7bc2c |
| RAG | 0.555 | Not recorded | 68fa79061e209131cea7bc2c |
| GenRead | 0.547 | Not recorded | 68fa79061e209131cea7bc2c |
| RAG | 0.547 | Not recorded | 68fa79061e209131cea7bc2c |
| No RAG | 0.545 | Not recorded | 68fa79061e209131cea7bc2c |
| RAG | 0.537 | Not recorded | 68fa79061e209131cea7bc2c |
| GenRead | 0.536 | Not recorded | 68fa79061e209131cea7bc2c |
| RobustRAG | 0.53 | Not recorded | 68fa79061e209131cea7bc2c |
| GenRead | 0.527 | Not recorded | 68fa79061e209131cea7bc2c |
| No RAG | 0.513 | Not recorded | 68fa79061e209131cea7bc2c |
| ASTUTE RAG | 0.513 | Not recorded | 68fa79061e209131cea7bc2c |
| Self-Route | 0.512 | Not recorded | 68fa79061e209131cea7bc2c |
| No RAG | 0.511 | Not recorded | 68fa79061e209131cea7bc2c |
| GenRead | 0.487 | Not recorded | 68fa79061e209131cea7bc2c |
| RAG | 0.483 | Not recorded | 68fa79061e209131cea7bc2c |
| RobustRAG | 0.464 | Not recorded | 68fa79061e209131cea7bc2c |
| RobustRAG | 0.4564 | Not recorded | 68fa79061e209131cea7bc2c |
| InstructRAG | 0.455 | Not recorded | 68fa79061e209131cea7bc2c |
| No RAG | 0.402 | Not recorded | 68fa79061e209131cea7bc2c |
| USC | 0.396 | Not recorded | 68fa79061e209131cea7bc2c |

### ASTUTE RAG

Accuracy: 0.617. Result ID: 6995b9813badfaffe6bab5a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### ASTUTE RAG

Accuracy: 0.599. Result ID: 6995b9813badfaffe6bab5b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### USC

Accuracy: 0.595. Result ID: 6995b9813badfaffe6bab5ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### ASTUTE RAG

Accuracy: 0.592. Result ID: 6995b9813badfaffe6bab5ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### InstructRAG

Accuracy: 0.588. Result ID: 6995b9813badfaffe6bab5a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773e1e209131cea71ed6.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### USC

Accuracy: 0.587. Result ID: 6995b9813badfaffe6bab59e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### Self-Route

Accuracy: 0.581. Result ID: 6995b9813badfaffe6bab5a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fa1e209131cea53df2.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### Self-Route

Accuracy: 0.576. Result ID: 6995b9813badfaffe6bab5aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fa1e209131cea53df2.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### InstructRAG

Accuracy: 0.567. Result ID: 6995b9813badfaffe6bab5b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773e1e209131cea71ed6.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RobustRAG

Accuracy: 0.565. Result ID: 6995b9813badfaffe6bab5a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73511e209131cea5bcf5.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### USC

Accuracy: 0.564. Result ID: 6995b9813badfaffe6bab5a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### Self-Route

Accuracy: 0.562. Result ID: 6995b9813badfaffe6bab5b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fa1e209131cea53df2.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### InstructRAG

Accuracy: 0.561. Result ID: 6995b9813badfaffe6bab5a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773e1e209131cea71ed6.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RAG

Accuracy: 0.555. Result ID: 6995b9813badfaffe6bab59d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.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: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### GenRead

Accuracy: 0.547. Result ID: 6995b9813badfaffe6bab5a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e791e209131cea40209.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RAG

Accuracy: 0.547. Result ID: 6995b9813badfaffe6bab5ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.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: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### No RAG

Accuracy: 0.545. Result ID: 6995b9813badfaffe6bab59c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RAG

Accuracy: 0.537. Result ID: 6995b9813badfaffe6bab5a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.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: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### GenRead

Accuracy: 0.536. Result ID: 6995b9813badfaffe6bab59f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e791e209131cea40209.md>)

Recorded evaluation configuration: {"LLM":"Claude 3.5 Sonnet (20240620)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RobustRAG

Accuracy: 0.53. Result ID: 6995b9813badfaffe6bab5b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73511e209131cea5bcf5.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### GenRead

Accuracy: 0.527. Result ID: 6995b9813badfaffe6bab5af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e791e209131cea40209.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### No RAG

Accuracy: 0.513. Result ID: 6995b9813badfaffe6bab5a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### ASTUTE RAG

Accuracy: 0.513. Result ID: 6995b9813badfaffe6bab5bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### Self-Route

Accuracy: 0.512. Result ID: 6995b9813badfaffe6bab5ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71fa1e209131cea53df2.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### No RAG

Accuracy: 0.511. Result ID: 6995b9813badfaffe6bab5ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Large (2407), 128B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### GenRead

Accuracy: 0.487. Result ID: 6995b9813badfaffe6bab5b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e791e209131cea40209.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RAG

Accuracy: 0.483. Result ID: 6995b9813badfaffe6bab5b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.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: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RobustRAG

Accuracy: 0.464. Result ID: 6995b9813badfaffe6bab5b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73511e209131cea5bcf5.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### RobustRAG

Accuracy: 0.4564. Result ID: 6995b9813badfaffe6bab5a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73511e209131cea5bcf5.md>)

Recorded evaluation configuration: {"LLM":"Gemini 1.5 Pro (002)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### InstructRAG

Accuracy: 0.455. Result ID: 6995b9813badfaffe6bab5b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773e1e209131cea71ed6.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### No RAG

Accuracy: 0.402. Result ID: 6995b9813badfaffe6bab5b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### USC

Accuracy: 0.396. Result ID: 6995b9813badfaffe6bab5b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc2c.md>)

Recorded evaluation configuration: {"LLM":"Mistral-Nemo (2407), 12B","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

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