# Recall of Human QA on INFOLOSSQA (test)

Source: [Recall of Human QA on INFOLOSSQA (test)](<https://www.sota2.com/research/sota/recall-of-human-qa-on-infolossqa-test>)

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

Data updated: 2026-02-26T06:01:18.555Z

Evaluation of model performance on the test split of the INFOLOSSQA dataset focusing on human question answering recall metrics (Full, Partial, No).

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 | Recall of Human QA |
| Dataset (including any stated split) | INFOLOSSQA (test) |
| Metric | Recall (Full) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Recall (Full)](<https://www.sota2.com/research/sota/recall-of-human-qa-on-infolossqa-test.md?metric=Recall%20(Full)>): Higher is better; unit: PERCENT.

- [Recall (Partial)](<https://www.sota2.com/research/sota/recall-of-human-qa-on-infolossqa-test.md?metric=Recall%20(Partial)>): Higher is better; unit: PERCENT.

- [Recall (No)](<https://www.sota2.com/research/sota/recall-of-human-qa-on-infolossqa-test.md?metric=Recall%20(No)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Recall (Full) | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4 | 0.281 | Not recorded | 68fa73771e209131cea5cb44 |
| NLI Pipeline | 0.229 | Not recorded | 68fa73771e209131cea5cb44 |
| Llama2-70B | 0.162 | Not recorded | 68fa73771e209131cea5cb44 |
| Mistral-7B | 0.142 | Not recorded | 68fa73771e209131cea5cb44 |

### GPT-4

Recall (Full): 0.281. Result ID: 6992e2563a6c314849122925.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb44.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727a1e209131cea56a1e.md>)

[Implementation](<https://github.com/openai/evals>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NLI Pipeline

Recall (Full): 0.229. Result ID: 6992e2563a6c314849122926.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb44.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb44.md>)

[Implementation](<https://infolossqa.ikim.nrw/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Llama2-70B

Recall (Full): 0.162. Result ID: 6992e2563a6c314849122924.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb44.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Mistral-7B

Recall (Full): 0.142. Result ID: 6992e2563a6c314849122923.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73771e209131cea5cb44.md>)

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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