# Cultural Awareness & Instruction Following on Arabic Cultural Value Alignment (test)

Source: [Cultural Awareness & Instruction Following on Arabic Cultural Value Alignment (test)](<https://www.sota2.com/research/sota/cultural-awareness-and-instruction-following-on-arabic-cultural-value-alignment-test>)

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

Data updated: 2026-03-18T08:42:30.922Z

Evaluation of model performance on cultural awareness and instruction following using the test split of the Arabic Cultural Value Alignment dataset, measured by the Cultural score.

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 | Cultural Awareness & Instruction Following |
| Dataset (including any stated split) | Arabic Cultural Value Alignment (test) |
| Metric | Cultural Score |
| Unit | SCALAR |
| 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

- [Cultural Score](<https://www.sota2.com/research/sota/cultural-awareness-and-instruction-following-on-arabic-cultural-value-alignment-test.md?metric=Cultural%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Cultural Score | Result date | Report paper |
| --- | --- | --- | --- |
| Fanar-27B | 4.32 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Allam-7B-Instruct-preview-v2 | 4.1 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Fanar-1-9B-Instruct | 3.86 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Qwen3-32B | 3.49 | Not recorded | 69ba31880636e5bf4afc07c4 |
| AceGPT-v2-70B-Chat | 3.37 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Gemma-3-27B-it | 3.34 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Jais-2-70B-Chat | 3.3 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Llama-3.3-70b-Instruct | 3.27 | Not recorded | 69ba31880636e5bf4afc07c4 |
| Karnak | 3.26 | Not recorded | 69ba31880636e5bf4afc07c4 |
| AceGPT-v2-32B-Chat | 3.25 | Not recorded | 69ba31880636e5bf4afc07c4 |

### Fanar-27B

Cultural Score: 4.32. Result ID: 69ba655847f34ce924a45c22.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

Recorded evaluation configuration: {"Size":"27B"}. This record does not assert independent reproduction.

### Allam-7B-Instruct-preview-v2

Cultural Score: 4.1. Result ID: 69ba655847f34ce924a45c20.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa742d1e209131cea603f7.md>)

Recorded evaluation configuration: {"Size":"7B"}. This record does not assert independent reproduction.

### Fanar-1-9B-Instruct

Cultural Score: 3.86. Result ID: 69ba655847f34ce924a45c21.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

Recorded evaluation configuration: {"Size":"9B"}. This record does not assert independent reproduction.

### Qwen3-32B

Cultural Score: 3.49. Result ID: 69ba655847f34ce924a45c28.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Size":"32B"}. This record does not assert independent reproduction.

### AceGPT-v2-70B-Chat

Cultural Score: 3.37. Result ID: 69ba655847f34ce924a45c25.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bbe1e209131cea8a274.md>)

Recorded evaluation configuration: {"Size":"70B"}. This record does not assert independent reproduction.

### Gemma-3-27B-it

Cultural Score: 3.34. Result ID: 69ba655847f34ce924a45c27.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

Recorded evaluation configuration: {"Size":"27B"}. This record does not assert independent reproduction.

### Jais-2-70B-Chat

Cultural Score: 3.3. Result ID: 69ba655847f34ce924a45c26.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

Recorded evaluation configuration: {"Size":"70B"}. This record does not assert independent reproduction.

### Llama-3.3-70b-Instruct

Cultural Score: 3.27. Result ID: 69ba655847f34ce924a45c29.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

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

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

Recorded evaluation configuration: {"Size":"70B"}. This record does not assert independent reproduction.

### Karnak

Cultural Score: 3.26. Result ID: 69ba655847f34ce924a45c24.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

Recorded evaluation configuration: {"Size":"40B"}. This record does not assert independent reproduction.

### AceGPT-v2-32B-Chat

Cultural Score: 3.25. Result ID: 69ba655847f34ce924a45c23.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31880636e5bf4afc07c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bbe1e209131cea8a274.md>)

Recorded evaluation configuration: {"Size":"32B"}. This record does not assert independent reproduction.

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