# Closed-book Question Answering on Ever Young

Source: [Closed-book Question Answering on Ever Young](<https://www.sota2.com/research/sota/closed-book-question-answering-on-ever-young>)

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

Data updated: 2026-04-13T09:57:00.503Z

Evaluation of model performance on the Ever Young dataset for Closed-book Question Answering, measured using the LLM metric.

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 | Closed-book Question Answering |
| Dataset (including any stated split) | Ever Young |
| Metric | LLM Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [LLM Score](<https://www.sota2.com/research/sota/closed-book-question-answering-on-ever-young.md?metric=LLM%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | LLM Score | Result date | Report paper |
| --- | --- | --- | --- |
| KNN | 81.67 | Not recorded | 69dc78a17d0172140ec78beb |
| Fine-tuning | 72.08 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy GEPA | 50.83 | Not recorded | 69dc78a17d0172140ec78beb |
| Initial prompt | 42.08 | Not recorded | 69dc78a17d0172140ec78beb |
| AIR | 42.08 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy BootstrapFewShot (#10) | 38.3 | Not recorded | 69dc78a17d0172140ec78beb |
| DSPy MIPROv2 | 37.5 | Not recorded | 69dc78a17d0172140ec78beb |
| TextGrad | 37.5 | Not recorded | 69dc78a17d0172140ec78beb |

### KNN

LLM Score: 81.67. Result ID: 69dcbdd547f34ce924c42022.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Inference Tokens (input / output) - Base Model":"3321 / 434"}. This record does not assert independent reproduction.

### Fine-tuning

LLM Score: 72.08. Result ID: 69dcbdd547f34ce924c42023.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) - Base Model":"36250 / 5945","Inference Tokens (input / output) - Base Model":"2123 / 319"}. This record does not assert independent reproduction.

### DSPy GEPA

LLM Score: 50.83. Result ID: 69dcbdd547f34ce924c42026.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a3a1e209131cea81ee3.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) - Base Model":"1098892 / 15248","Train Tokens (input / output) - Reflection Model":"118233 / 88819","Inference Tokens (input / output) - Base Model":"58193 / 623"}. This record does not assert independent reproduction.

### Initial prompt

LLM Score: 42.08. Result ID: 69dcbdd547f34ce924c42021.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Inference Tokens (input / output) - Base Model":"2123 / 608"}. This record does not assert independent reproduction.

### AIR

LLM Score: 42.08. Result ID: 69dcbdd547f34ce924c42028.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) - Embed Model":"3878 / -","Train Tokens (input / output) - Base Model":"123152 / 2281","Train Tokens (input / output) - Reflection Model":"19665 / 31183","Inference Tokens (input / output) - Base Model":"68063 / 382"}. This record does not assert independent reproduction.

### DSPy BootstrapFewShot (#10)

LLM Score: 38.3. Result ID: 69dcbdd547f34ce924c42024.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d01e209131cea4d60e.md>)

[Implementation](<https://github.com/stanfordnlp/dspy>)

Recorded evaluation configuration: {"Train Tokens (input / output) - Base Model":"7275 / 223","Inference Tokens (input / output) - Base Model":"21983 / 592"}. This record does not assert independent reproduction.

### DSPy MIPROv2

LLM Score: 37.5. Result ID: 69dcbdd547f34ce924c42025.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75121e209131cea65828.md>)

Recorded evaluation configuration: {"Train Tokens (input / output) - Base Model":"906850 / 74221","Inference Tokens (input / output) - Base Model":"14573 / 604"}. This record does not assert independent reproduction.

### TextGrad

LLM Score: 37.5. Result ID: 69dcbdd547f34ce924c42027.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78a17d0172140ec78beb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73981e209131cea5d7cd.md>)

[Implementation](<https://github.com/zou-group/textgrad>)

Recorded evaluation configuration: {"Train Tokens (input / output) - Base Model":"405807 / 2925","Train Tokens (input / output) - Reflection Model":"601023 / 684425","Inference Tokens (input / output) - Base Model":"127373 / 356"}. This record does not assert independent reproduction.

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