# Factual Precision Evaluation on Culture & Entertainment

Source: [Factual Precision Evaluation on Culture & Entertainment](<https://www.sota2.com/research/sota/factual-precision-evaluation-on-culture-and-entertainment>)

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

Data updated: 2026-02-26T05:44:01.968Z

Evaluation of model performance on factual precision using the Culture & Entertainment dataset, measured by the FACTSCORE 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 | Factual Precision Evaluation |
| Dataset (including any stated split) | Culture & Entertainment |
| Metric | FACTSCORE |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [FACTSCORE](<https://www.sota2.com/research/sota/factual-precision-evaluation-on-culture-and-entertainment.md?metric=FACTSCORE>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FACTSCORE | Result date | Report paper |
| --- | --- | --- | --- |
| MistralINST | 0.887 | Not recorded | 68fa753e1e209131cea66b85 |
| MistralINST | 0.879 | Not recorded | 68fa753e1e209131cea66b85 |
| GPT-2 | 0.871 | Not recorded | 68fa753e1e209131cea66b85 |
| MistralINST | 0.815 | Not recorded | 68fa753e1e209131cea66b85 |
| MistralINST | 0.797 | Not recorded | 68fa753e1e209131cea66b85 |
| GPT-2 | 0.727 | Not recorded | 68fa753e1e209131cea66b85 |
| MistralINST | 0.404 | Not recorded | 68fa753e1e209131cea66b85 |
| MistralINST | 0.264 | Not recorded | 68fa753e1e209131cea66b85 |
| GPT-2 | 0.0341 | Not recorded | 68fa753e1e209131cea66b85 |
| GPT-2 | 0.01 | Not recorded | 68fa753e1e209131cea66b85 |

### MistralINST

FACTSCORE: 0.887. Result ID: 699383ec3a6c314849168440.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"INFO","CORE":"w/o"}. This record does not assert independent reproduction.

### MistralINST

FACTSCORE: 0.879. Result ID: 699383ec3a6c314849168442.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"REP","CORE":"w/o"}. This record does not assert independent reproduction.

### GPT-2

FACTSCORE: 0.871. Result ID: 699383ec3a6c314849168444.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"INFO","CORE":"w/o"}. This record does not assert independent reproduction.

### MistralINST

FACTSCORE: 0.815. Result ID: 699383ec3a6c31484916843e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"NORMAL","CORE":"w/o"}. This record does not assert independent reproduction.

### MistralINST

FACTSCORE: 0.797. Result ID: 699383ec3a6c31484916843f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"NORMAL","CORE":"w/"}. This record does not assert independent reproduction.

### GPT-2

FACTSCORE: 0.727. Result ID: 699383ec3a6c314849168446.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"REP","CORE":"w/o"}. This record does not assert independent reproduction.

### MistralINST

FACTSCORE: 0.404. Result ID: 699383ec3a6c314849168441.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"INFO","CORE":"w/"}. This record does not assert independent reproduction.

### MistralINST

FACTSCORE: 0.264. Result ID: 699383ec3a6c314849168443.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"REP","CORE":"w/"}. This record does not assert independent reproduction.

### GPT-2

FACTSCORE: 0.0341. Result ID: 699383ec3a6c314849168445.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"INFO","CORE":"w/"}. This record does not assert independent reproduction.

### GPT-2

FACTSCORE: 0.01. Result ID: 699383ec3a6c314849168447.

[Reporting paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa753e1e209131cea66b85.md>)

[Implementation](<https://github.com/zipJiang/adversarial-factuality>)

Recorded evaluation configuration: {"Scenario":"REP","CORE":"w/"}. This record does not assert independent reproduction.

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